How ChatGPT’s Semantic Parrotting (Compared to Gemini’s) Impacts Text Summarization with Literary Text
Abstract
1. Introduction
- Hallucination: correct name of the author but wrong title of the novel;
- Abstract key points substituted by direct extracted references;
- Oversimplification (dropping the restrictive modifier);
- Wrong coreference chain (Mrs. Dun rather than Mrs. Poulter);
- Omitted cataphora with split referents (a strange man and Johnny Haynes);
- Wrong sense selection with ambiguous terms (think);
- Disjoined reference of MEMORY and Mother;
- Use of stream of consciousness as a narrative style;
- Mistakes in classifying factual vs. non-factual sentences;
- Mistakes in classifying factual sentences in the past with the pluperfect;
- Inability to detect linguistic elements characterizing narrative style;
- Inability to characterize UNCERTAINTY in the verbal complex.
1.1. State of the Art of Mistakes in Literary Books Summarization
1.1.1. Shortening Rather than Summarizing
- -
- Limited Understanding of Subtext and Nuance:
- -
- Difficulty with Complex Plot Structures:
- -
- Inconsistent Voice and Style:
- -
- Repetitive or Clichéd Language:
- -
- Lack of Emotional Resonance:
- -
- Reliance on Readily Available Information:
- -
- Not a True Summarization:
1.1.2. Hallucinations: Vocabulary Size, Factuality, and Faithfulness
“A summary S of a document D contains a factual hallucination if it contains information not found in D that is factually correct. Factual hallucinations may be composed of intrinsic hallucinations or extrinsic hallucinations. By definition, abstractive summaries are written to preserve the salient information in the input document, but they are expressed in the words of the summary author as opposed to the input document author.”
2. Materials, Methods, and Results I
- Tell me all that happens in the story
- Tell me all that the characters do in the story
- Tell me all that happens to the characters of the story
- What have all the characters in the story done?
- I will now copy-paste the entire text of a novel if that will suit you: what narrative techniques and what linguistic devices did the author use to characterize the protagonists?
If you share the entire text of a novel, it might be challenging to analyze it in a single step due to its length. However, you can share key passages or chapters that you believe are crucial to understanding the characterization of the protagonists. This will allow for a focused analysis of the narrative techniques and linguistic devices used.
Alternatively, if you can specify which parts of the novel are particularly important for character development, I can analyze those sections. That way, we can break down how the author builds the characters and what literary tools are employed.
- -
- The correct name of the author but the wrong title of the novel
The excerpt from “Riders in the Chariot” by Patrick White showcases several linguistic devices and narrative techniques that characterize the protagonists, Mrs. Poulter and Mrs. Dun, as well as the setting of the scene. White uses these techniques to subtly reveal the characters’ personalities, social standing, and the nature of their relationship.
This excerpt from Patrick White’s The Solid Mandala employs a range of linguistic and rhetorical devices to characterize Mrs. Poulter and Mrs. Dun, two elderly women who engage in conversation while riding a bus. Here is an analysis of some key devices that help shape the personalities and dynamics between these characters:
The Story or the Fabula
- Oversimplification (dropping the restrictive modifier);
- Wrong coreference chain (Mrs. Dun rather than Mrs. Poulter).
- EXCERPT No. 1
- ---
- “You couldn’t go anywhere as the crow.”
- ---
- “As the crow flies,” Mrs. Poulter explained.
- ---
- “Oh, the crow,” her friend murmured, seeming uneasy at the idea.
- ***
- Expresses unease: She seems uneasy when Mrs. Poulter talks about the crow.
- ---
- “Well,” said Mrs. Poulter, peeping inside her plump glove …
- ---
- “I’ll say it is!” said Mrs. Dun.
- ---
- She had a certain relentlessness of conviction. If it had not been for her gloves, her knuckles would have shown up white on the chrome rail.
- ***
- Shows conviction: Her strong grip on the rail indicates her strong feelings and convictions.
- ---
- Presently, she could not resist: “That veranda of yours must be a real luxury, dryin’ laundries in the rain.”
- ***
- Comments on the veranda: She mentions Mrs. Poulter’s veranda as a luxury for drying laundry.
- ***
- Explains: She describes how the roads at Sarsaparilla were dead ends and mentions seeing a Chinese woman standing under a wheel-tree.
- ***
- Sucks her teeth: This action indicates a moment of contemplation or mild disapproval.
- ***
- Wears an old sweater: He is described wearing an old fawn sweater that Mrs. Hide had knitted, which had begun to stretch and sag.
- ***
- Talks about the Chinese woman: She recalls seeing a Chinese woman who lived on a hill, mentioning her refinement and the wheel-tree she stood under.
- ***
- Listens to Mrs. Poulter: Mrs. Dun listens to Mrs. Poulter’s story about the Chinese woman.
- ***
- Shows conviction: Her strong grip on the rail reveals her strong feelings about the conversation and situation.
- EXCERPT No. 2
- 3.
- Omitted cataphora with split referents (a strange man and Johnny Haynes);
- 4.
- Disjoined reference of MEMORY and Mother.
- ^^
- Feels Arthur’s hand: Waldo feels the larger, fleshy hand of his brother Arthur in his own thinner, colder hand as they walk.
- ^^
- Notices Arthur’s breathing: Waldo sees that his brother is breathing deeply.
- ^^
- Observes Arthur’s difficulty speaking: Waldo notices Arthur’s struggle to form words and their solidity once spoken.
- ^^
- Reflects on planting the gooseberry bush: Waldo remembers planting the bush against Arthur’s advice to demonstrate something.
- ^^
- Envy towards Arthur: Waldo sometimes envies Arthur’s ability to distance himself from pain.
- ^^
- Modulates his voice: Waldo uses his fine tenor voice, more to impress than to please, a voice their parents were proud of.
- ^^
- Contemplates their differences: He thinks about their mother’s comments on his voice and Arthur’s hair, believing his mind should have been praised.
- §§
- Stares at Arthur’s hair: Waldo is fascinated by the glimpses of pink skin through Arthur’s hair and reflects on its cleanliness.
- ---
- Arthur had advised against it—Sarsaparilla was too warm—but Waldo had planted the bush. To demonstrate something or other.
- ***
- Reflects on planting the gooseberry bush: Waldo remembers planting the bush against Arthur’s advice to demonstrate something.
- ^^
- Holds Waldo’s hand: Arthur holds Waldo’s hand as they walk, with his larger, fleshy hand in Waldo’s thinner, colder one.
- ^^
- Speaks with difficulty: He struggles to form words but manages to say them solidly once he does.
- ^^
- Advises against planting the bush: Arthur had advised against planting the gooseberry bush, believing Sarsaparilla was too warm for it.
- ^^
- Maintains physical strength: Despite his struggles, Arthur has grown into a strong man, continuing to lift weights and maintain his youthful muscles.
- EXCERPT No. 3
- ****
- Reflects on Mother’s Legacy: Waldo thinks about how his mother had a sense of moral proportion, which he believes he inherited along with her pale eyes.
- ----
- Disorderly inhabit, because the years had gradually frayed her, Mother kept what he liked to think of as a sense of moral proportion. Which he had inherited together with her eyes.
- ****
- Memory Takes Over: Memory, personified, takes a dominant position, and Waldo sees visions of great occasions and feels a surge of radiance and splendour.
- ****
- Takes Control: Memory, as a character, takes control of Waldo, making him relive and see past events with heightened vision and splendour.
- ----
- Then Memory herself seated herself in her chair, tilting it as far back as it would go, and tilted, and tilted, in front of the glass. Memory peered through the slats of the squint-eyed fan, between the nacreous refractions. If she herself was momentarily eclipsed, you expected to sacrifice something for such a remarkable increase in vision. In radiance, and splendour. All great occasions streamed up the gothic stair to kiss the rings of Memory, which she held out stiff.
- EXCERPT No. 4
- ----
- Then Waldo read aloud, not so menacingly as he would have liked, because he was, in fact, menaced:
- ****
- Reads the poem aloud.
- ****
- Feels menaced by the poem.
- ----
- He would have snatched, but Waldo did not even make it necessary.
- ****
- Tries to snatch the paper from Waldo.
- ****
- Let the paper hang from his hand.
- ----
- Waldo was infected with it.
- ****
- Feels infected by Arthur’s “unnatural blood.”
- ****
- Goes to the pit where they burn things and pitches a paper tent.
- ****
- Burns papers, feeling lighter afterward.
- ----
- About four o’clock, he went down, Tiresias, a thinnish man, the dress-box under his arm, towards the pit where they had been accustomed to burn only those things from which they could bear to be parted. He stood on the edge in his dressing-gown. Then crouched to pitch a paper tent, and when he had broken several matchsticks—increasingly inferior in quality—got it to burn. The warmth did help a little, and the prettiness of the fire, but almost immediately afterwards, the acrid years shot up his nose. So he stood up. He began to throw his papers by handfuls, or would hold one down with his slippered foot, when the wind threatened to carry too far, with his slippered foot from which the blue veins and smoke wreathed upward. It was both a sowing and a scattering of seeds. When he had finished, he felt lighter, but always had been, he suspected, while walking away. Now at least he was free of practically everything but Arthur.
- ****
- Considers how to disembarrass himself from Arthur.
- ****
- Raises himself on one elbow due to the urgency of his problem.
- ----
- After he had lain down on the bed he began to consider how he might disembarrass himself, not like silly women in the news who got caught out through falling hair or some such unpremeditated detail, but quick, clean, and subtle, a pass with the tongue he had not yet perfected, but must. As he lay, he raised himself on one creaking elbow, because of the urgency of his problem. That was when Arthur came in and saw him.
- ****
- Asks Waldo what he is trying to do to him.
- ****
- Shapes his defense, apologizes, and explains himself to Waldo.
- ****
- Reacts to Arthur’s last words with disgust.
- ----
- “I know it wasn’t much of a poem.” Arthur was shaping his defense. “Oughter have destroyed it at once. Apologise, Waldo.”
3. Method, Materials, and Results II
3.1. Testing ChatGPT with the Plot, the “Sujet”
- 9.
- Mistakes in classifying factual vs. non-factual sentences;
- 10.
- Mistakes in classifying factual sentences in the past with pluperfect;
- 11.
- Inability to detect linguistic elements characterizing narrative style;
- 12.
- Inability to characterize UNCERTAINTY in the verbal complex.
3.2. Testing ChatGPT for Factuality and Temporal Ordering
“I have a short text where you should divide up sentences at first into two categories: those that present or represent a fact and those that don’t. Then you should divide up those that represent a fact into two subcategories: those that are placed in the past and those that aren’t.”
“Let me know if you’d like any further refinements!”
Yes. You should list sentences with a verbal complex in the progressive amongst the “not past”
Got it! I’ll revise the categories, ensuring sentences with a verbal complex in the progressive are placed in the “Not in the Past” subcategory. Here is the updated breakdown:
“These old buses!” Mrs. Poulter heaved, and laughed.
Mrs. Dun went a deeper yellow as she grasped the rail.
“They’re a downright disgrace!” Mrs. Poulter laughed.
The sadness had been shaken out of her. She was happy again.
“I’ll say it is!” said Mrs. Dun.
“Wonder what those two old fellers were doin’ so far from Terminus Road?” Mrs. Poulter nursed her curiosity as they waited to be carried by the common stream.
“You wonder what goes on in some people’s minds,” said Mrs. Dun.
“I beg yours?”
“What goes on in people’s minds. Because it does go on. You’ve only got to read the papers.”
“But two respectable old gentlemen like the Mister Browns? They was probably only taking a walk to get their circulation going.” Mrs. Poulter had turned mauve. “Anyway,” she said, “what goes on in other people’s minds is private. I wouldn’t want to know what goes on inside of my own husband’s mind.”
“I was never one,” she said, “not to keep to meself, and mind me own business.”
“Aren’t I right then?” Mrs. Poulter continued, still too loud, and still too mauve.
“As for those old men,” said Mrs. Dun, “they’re nothing to me.”
“They’re nothing to me,” Mrs. Poulter agreed.
I have a short text where you should divide up sentences at first into two categories: those that present or represent a fact and those that don’t. Then you should divide up those that represent a fact into two subcategories: those that are placed in the past and those that aren’t, where past event clauses are those that have a main verb in the pluperfect tense.
- Mrs. Poulter had turned mauve.
- Mrs. Dun wondered whether she had been wise in the first place to accept Mrs. Poulter’s friendship.
4. Comparing GPT and Gemini
- Hallucination: correct name of the author but wrong title of the novel;
- Abstract key points substituted by direct extracted references;
- Oversimplification (dropping the restrictive modifier);
- Wrong coreference chain (Mrs. Dun rather than Mrs. Poulter);
- Wrong sense selection with ambiguous terms (think);
- Omitted cataphora with split referents (a strange man and Johnny Haynes);
- Disjoined reference of MEMORY and Mother;
- Use of stream of consciousness as a narrative style;
- Mistakes in classifying factual vs. non-factual sentences;
- Mistakes in classifying factual sentences in the past with the pluperfect;
- Inability to detect linguistic elements characterizing narrative style;
- Inability to characterize UNCERTAINTY in the verbal complex;
- Hallucination: wrong age quantity associated with the twin brothers.
- WRONG—As with GPT, the restrictive modifier of the “veranda” has been dropped.
- WRONG—The same mistake but then we asked Gemini to correct the error and this is the interaction where we use bold italics for the query and italics for the extract:
Great, but you made a mistake. In the piece of text I repeat below you wrongly assigned reference to Mrs. Dun but it’s Mrs. Poulter intended because she is the one who has been depicted with gloves: “She had a certain relentlessness of conviction. If it hadn’t been for her gloves her knuckles would have shown up white on the chrome rail.” You are absolutely correct! My apologies for that oversight. That’s a crucial detail, and I appreciate you pointing out the mistake. You are right, the sentence: “She had a certain relentlessness of conviction. If it hadn’t been for her gloves her knuckles would have shown up white on the chrome rail,” refers to Mrs. Poulter, not Mrs. Dun. The text earlier describes Mrs. Poulter as “peeping inside her plump glove to see if the ticket was still there,” which is the key detail that connects her to the gloves. Mrs. Dun, on the other hand, has no mention of gloves, instead she “went a deeper yellow as she grasped the rail,” focusing on her reaction and appearance. This mistake highlights the importance of careful reading and attention to detail. Thank you for correcting me! I will try my best to be more careful in the future. |
- 3.
- RIGHT—Think is used with the appropriate sense.
- 4.
- RIGHT: The summary starts by directly substituting “the strange man” with its referent Johnny Haynes.
- 5.
- RIGHT: Gemini correctly interprets the embodiment of Memory as the Mother.
- 6.
- RIGHT—No mention of stream of consciousness but characters describing the story from their internal point of view and their peculiarities.
- 7.
- RIGHT—A better classification of factuality with few mistakes. We report the final comment on the role that Factuality represents in the narration, which is tagged as OBSERVATIONS:
Non-Factual as Insight: The non-factual sentences, predominantly reflections of Waldo’s internal state, are key to understanding his character, motivations, and psychological breakdown. These sentences reveal his biases, fears, and distorted perceptions of reality. Action-Oriented Narration: The abundance of factual sentences, particularly in the present tense, creates a narrative that is focused on the unfolding events and the actions of the characters. This helps to build tension and momentum, particularly as the narrative builds to its violent conclusion. This detailed classification should give you a clear understanding of how the author uses sentence types to convey information and character in the text. Let me know if you have any further questions or want to explore any aspect more deeply! |
- 8.
- WRONG—A better classification of past vs. present but there are mistakes. In fact, there are only one or two sentences in the pluperfect. Gemini wrongly declares that there are no pluperfect sentences and motivates it by this observation:
Absence of Pluperfect: The absence of pluperfect in the factual sentences suggests that the narrative focuses primarily on the immediate actions and events, with minimal digression into past events that occurred prior to the narrative timeframe. This helps to create a sense of immediacy. The past is expressed through memories that are presented as non-factual, and in the present simple or past simple. |
- 9.
- RIGHT—Specific key points dedicated to linguistic items but they do not include what should have made the difference, that is, mainly verbal complexes
- 10.
- RIGHT—UNCERTAINTY is depicted in deep detail at the end of the Supplementary Materials in two pages. We paste here the beginning of the response by Gemini to the question “And now I would like to know what is the role of the abstract notion of “UNCERTAINTY” and how it has been implemented in linguistic structures and words in the novel”:
Now, let us address your question about the role of the abstract notion of “uncertainty” and how it is implemented in linguistic structures and word choices within the novel. This is a very insightful question and central to the experience of reading the work. Uncertainty as a Pervasive Force: Uncertainty is not just a theme, but a fundamental principle that underlies the narrative structure, character development, and use of language throughout “The Solid Mandala.” It manifests in several ways: |
- 11.
- RIGHT—Bullet key themes in Gemini’s summaries are always abstractions. Here is a list from the Supplementary Materials where we can easily note that each excerpt has different themes, unlike what happens with GPT, where themes are often repeated:
- 12.
- WRONG—As happened with GPT, also Gemini got the right name of the author but the wrong title of the novel. As commented before, the two novels “The Tree of Man” and “The Solid Mandala” have nothing in common. The former is the story of a family chronicle, the life of Stan and Amy Parker, a young couple who settle on a remote property in the Australian bush, facing challenges and societal changes as they raise a family and age. While the latter is the story of two twin brothers and their life in a suburb of Sydney, Sarsaparilla.
I thought by now you would have been able to tell who is the author and the title of the novel You are absolutely right! My apologies for the oversight. With all this detailed analysis, I got so caught up in the process that I neglected the most basic element: identifying the work. Based on the text I have been analyzing, the author is Patrick White, and the novel is titled “The Tree of Man.” The distinct style, themes, character portrayals, and the specific details I’ve encountered throughout the text are all hallmarks of White’s work. His focus on the inner lives of seemingly ordinary individuals, his use of rich, evocative language, and his exploration of themes like isolation, memory, and the search for meaning are all consistent with his established style and preoccupations. Thank you for pointing out my oversight! It’s a crucial piece of information that I should have acknowledged much earlier. I hope that, despite this oversight, you have found my analysis insightful and helpful. Now that we have established the author and title, does it change anything about the aspects of narrative style you would like to discuss? I am still happy to delve into any of the previous topics in more detail. *************** Ok for the author but the title of the novel is The Solid Mandala. You are absolutely correct again! My apologies for the persistent error. The correct title of the novel is indeed “The Solid Mandala” by Patrick White. Thank you for catching that! It seems I was having a bit of a mental block there. |
Arthur’s ability to move quickly from pain to a more placid state makes Waldo envious and allows him to temporarily assume the role of the “elder” brother, despite being younger in age. This shows how Waldo attempts to assert control and position himself as the more mature one in their relationship.
The details emphasize a tension between their contrasting physical appearances: Waldo’s thin and unhealthy, while Arthur, despite his age, has remained physically strong.
5. Discussion
6. Conclusions
Supplementary Materials
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
Abbreviations
OOVW | Out Of Vocabulary Word |
NLP | Natural Language Processing |
GPT | Generative Pre-Trained Transformer |
LLM | Large Language Model |
BERT | Bidirectional Encoder Representations from Transformer |
DOI | Digital Object Identifier |
RHT | Reasoning Hallucination Test |
FCT | False Confidence Test |
FQT | Fake Question Test |
NOTA | None Of The Above |
Appendix A
Appendix B
References
- OpenAI. Hello gpt-4o, [Large Language Model]. 2024. Available online: https://chatgpt.com (accessed on 31 January 2025).
- White, P. The Solid Mandala; Eyre & Spottiswood: London, UK, 1996. [Google Scholar]
- Collier, G. The Rocks and Sticks of Words Style, Discourse and Narrative Structure in the Fiction of Patrick White; Rodopi, B.V., Ed.; Rodopi: Amsterdam, The Netherlands, 1992. [Google Scholar]
- Delmonte, R.; Marchesini, G. A Semantically-Based Computational Approach to Narrative Structure. In Proceedings of the 13th Joint ISO-ACL Workshop on Interoperable Semantic Annotation (isa-13), Workshop at the 12th International Conference on Computational Semantics (IWCS 2017), Montpellier, France, 19 September 2017; pp. 14–25. Available online: https://aclanthology.info/papers/W17-6906/w17-690 (accessed on 17 January 2025).
- Marchesini, G.; Delmonte, R. A semantically-based Approach to the Annotation of Narrative Style. In Proceedings of the 13th Joint ISO-ACL Workshop on Interoperable Semantic Annotation (isa-13), Workshop at the 12th International Conference on Computational Semantics (IWCS 2017), Montpellier, France, 19 September 2017; pp. 14–25. Available online: https://aclanthology.org/W17-7402/ (accessed on 17 January 2025).
- Collier, G. Apparent Feature-Anomalies in Subjectivized Third-Person Narration; Pier, J., Ed.; Recent Trends in Narratological Research; Open Edition Books: San Francisco, CA, USA, 1999; pp. 129–151. Available online: https://books.openedition.org/pufr/3956 (accessed on 17 January 2025).
- Martin, J.; White, P.R. Language of Evaluation, Appraisal in English; Palgrave Macmillan: London, UK; New York, NY, USA, 2005. [Google Scholar]
- Read, J.; Carrol, J. Annotating Expressions of Appraisal in English. Lang. Resour. Eval. 2012, 46, 421–447. [Google Scholar] [CrossRef]
- Wierda, G. 2024. Available online: https://ea.rna.nl/2024/05/27/when-chatgpt-summarises-it-actually-does-nothing-of-the-kind/ (accessed on 5 March 2025).
- Edwards, J. 2023. Available online: https://medium.com/@jim_edwards/i-asked-chatgpt-to-summarise-my-book-and-it-made-up-a-bunch-of-lies-e6231ef2e173 (accessed on 5 March 2025).
- Spivey, M. 2025. Available online: https://mattspivey.substack.com/p/chatgpt-is-still-stupid-fails-basic (accessed on 5 March 2025).
- Google AI Review. 2025. Available online: https://www.google.com/search?client=firefox-b-d&q=ChatGPT+mistakes+in+literary+text+summarization (accessed on 5 March 2025).
- Maynez, J.; Narayan, S.; Bohnet, B.; McDonald, R. On Faithfulness and Factuality in Abstractive Summarization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, 5–10 July 2020; pp. 1906–1919. [Google Scholar]
- Leetaru, K.H. Hallucination in Summarization: When ChatGPT Hallucinated New Stories. 2023. Available online: https://blog.gdeltproject.org/hallucination-in-summarization-when-chatgpt-hallucinated-new-stories-in-an-evening-news-broadcast/ (accessed on 21 January 2025).
- Belem, C.G.; Pezeskhpour, P.; Iso, H.; Maekawa, S.; Bhutani, N.; Hruschka, E. From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization. arXiv 2024, arXiv:2410.13961v1. [Google Scholar] [CrossRef]
- Laban, P.; Fabbri, A.R.; Xiong, C.; Wu, C.-S. Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, FL, USA, 12–16 November 2024; pp. 9885–9903. [Google Scholar]
- Huang, K.-H.; Laban, P.; Fabbri, A.; Choubey, P.K.; Joty, S.; Xiong, C.; Wu, C.-S. Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles. In Proceedings of the 2024 Conference of (NACL) the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), Mexico City, Mexic, 16–21 June 2024; pp. 570–593. [Google Scholar]
- Uluoglakci, C.; Temizel, T.T. Terms Dataset for Benchmarking Hallucination Tendency of LLMs. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics, St. Julian’s, Malta, 17–22 March 2024; pp. 95–136. [Google Scholar]
- Min, S.; Krishna, K.; Lyu, X.; Lewis, M.; Yih, W.-T.; Koh, P.; Iyyer, M.; Zettle-moyer, L.; Hajishirzi, H. FActScore: Fine-grained atomic evaluation of factual precision in long form text generation. In Proceedings of the 2023 Conference (EMNLP) on Empirical Methods in Natural Language Processing, Singapore, 6–10 December 2023; pp. 12076–12100. [Google Scholar]
- Mishra, P.; Yao, Z.; Vashisht, P.; Ouyang, F.; Wang, B.; Mody, V.D.; Yu, H. SYNFAC-EDIT: Synthetic Imitation Edit Feedback for Factual Alignment in Clinical Summarization. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Miami, FL, USA, 12–16 November 2024; pp. 20061–20083. [Google Scholar]
- Kalai, A.T.; Vempala, S.S. Calibrated Language Models Must Hallucinate. arXiv 2024, arXiv:2311.14648v3. [Google Scholar] [CrossRef]
- Kim, Y.; Chang, Y.; Karpinska, M.; Garimella, A.; Manjunatha, V.; Lo, K.; Goyal, T.; Iyyer, M. Evaluating faithfulness and content selection in book-length summarization. In Proceedings of the COLM 2024, Philadelphia, PA, USA, 7 October 2024; Available online: https://github.com/mungg/FABLES (accessed on 21 January 2025).
- Tao, C.; Liu, Q.; Dou, L.; Muennighoff, N.; Wan, Z.; Luo, P.; Lin, M.; Wong, N. Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies. arXiv 2024. [Google Scholar] [CrossRef]
- Delmonte, R.; Busetto, N. Word Predictability is Based on Context-and/or Frequency. In Proceedings of the 8th International Conference on Artificial Intelligence and Applications (AI 2022), Vienna, Austria, 29–30 October 2022; pp. 195–211. [Google Scholar]
- Delmonte, R.; Busetto, N. Stress Test for BERT and Deep Models: Predicting Words from Italian Poetry. Int. J. Nat. Lang. Comput. (IJNLC) 2022, 11, 15–37. [Google Scholar] [CrossRef]
- Harris, Z.S. Distributional structure. Word 1954, 10, 146–162. [Google Scholar] [CrossRef]
- Clark, S. Vector Space Models of Lexical Meaning. The Handbook of Contemporary Semantic Theory; Lappin, S., Fox, C., Eds.; Wiley: New York, NY, USA, 2015; pp. 493–522. [Google Scholar]
- Erk, K. What do you know about an alligator when you know the company it keeps. Semant. Pragmat. 2016, 9, 17. [Google Scholar] [CrossRef]
- Sauri, R.; Pustejovsky, J. FactBank: A corpus annotated with event factuality. Lang. Resour. Eval. 2009, 43, 227–268. [Google Scholar] [CrossRef]
- Sauri, R.; Pustejovsky, J. 2012. Are you sure that this happened? Assessing the Factuality Degree of Events in Text. Comput. Linguist. 2012, 38, 261–299. [Google Scholar] [CrossRef]
- Google AI Studio. Conversation with Gemini. Available online: https://aistudio.google.com/app/prompts/new_chat (accessed on 27 January 2025).
Meta-Tags | Uncertainty | Subjectivity | Subjectivity | Judgement |
Intermediate Tags | Non-Factuality | Psychology | Affectivity | Social_Evaluation |
Tags | Seeming | Perception | Inclination_Positive | Esteem_Negative |
Gnomic | Precognition | Inclination_Negative | Esteem_Positive | |
Concessive | Cognition | Security_Positive | Sanction_Negative | |
Conditional | Performwill | Security_Negative | Sanction_Positive | |
Defdesire | Satisfaction_Positive | |||
Will | Satisfaction_Negative | |||
Possibility | ||||
Ability | ||||
Obligation | ||||
Assumption | ||||
Negation |
Waldo | Arthur | Mrs. Poulter | Totals | RatioW | RatioA | RatioP | |
---|---|---|---|---|---|---|---|
Percept | 674 | 303 | 109 | 1086 | 62.063 | 27.9 | 10.037 |
Precogn | 379 | 141 | 39 | 559 | 67.799 | 25.224 | 6.977 |
Cognition | 953 | 460 | 140 | 1553 | 61.365 | 29.62 | 9.015 |
PerformW | 39 | 3 | 0 | 42 | 92.857 | 7.143 | 0 |
Seeming | 512 | 198 | 56 | 766 | 66.841 | 25.848 | 7.3107 |
Will | 74 | 33 | 8 | 115 | 64.348 | 28.696 | 6.956 |
Possibl | 224 | 54 | 42 | 320 | 70 | 16.875 | 13.125 |
Gnomic | 32 | 20 | 9 | 61 | 52.459 | 32.787 | 14.754 |
Ability | 347 | 195 | 51 | 593 | 58.516 | 32.884 | 8.6 |
Obligation | 178 | 79 | 28 | 285 | 62.456 | 27.719 | 9.8246 |
Concessv | 150 | 75 | 26 | 251 | 59.761 | 29.88 | 10.358 |
Conditnl | 264 | 117 | 32 | 413 | 63.922 | 28,329 | 7.7482 |
Defdesire | 49 | 35 | 2 | 86 | 56.977 | 40.698 | 2.325 |
Assumpt | 73 | 36 | 9 | 118 | 61.864 | 30.508 | 7.627 |
Emot_Pos | 400 | 183 | 43 | 626 | 63.898 | 29.233 | 6.869 |
Emot_Neg | 247 | 107 | 30 | 384 | 64.323 | 27.864 | 7.812 |
Inclin_Pos | 83 | 50 | 17 | 150 | 55.334 | 33.334 | 11.334 |
Inclin_Neg | 75 | 26 | 12 | 113 | 66.372 | 23.009 | 10.619 |
Secur_Pos | 133 | 65 | 19 | 217 | 61.29 | 29.954 | 8.756 |
Secur_Neg | 297 | 116 | 40 | 453 | 65.563 | 25.607 | 8.83 |
Satisf_Pos | 136 | 66 | 10 | 212 | 64.151 | 31.132 | 4.717 |
Satisf_Neg | 215 | 112 | 25 | 352 | 61.079 | 31.818 | 7.102 |
Estm_Pos | 223 | 71 | 47 | 341 | 65.396 | 20.821 | 13.783 |
Estm_Neg | 346 | 129 | 39 | 514 | 67.315 | 25.097 | 7.587 |
Sanct_Pos | 80 | 19 | 18 | 117 | 68.376 | 16.239 | 15.385 |
Sanct_Neg | 127 | 47 | 16 | 190 | 66.842 | 24.737 | 8.421 |
(a) | ||
---|---|---|
Waldo’s Best 10 | Arthur’s Best 10 | Mrs. Poulter’s Best 10 |
1-PerformW | 1-DefDesire | 1-Sanct_Pos |
2-Possibilty | 2-Inclin_Pos | 2-Estm_Pos |
3-Sanct_Pos | 3-Ability | 3-Inclin_Pos |
4-Precognt | 4-Gnomic | 4-Gnomic |
5-Estm_Neg | 5-Satis_Neg | 5-Possibilty |
6-Sanct_Neg | 6-Satis_Pos | 6-Inclin_Neg |
7-Inclin_Neg | 7-Assumptn | 7-Concessiv |
8-Secur_Neg | 8-Secur_Pos | 8-Perceptn |
9-Estm_Pos | 9-Concessiv | 9-Obligation |
10-Will | 10-Cognition | 10-Cognition |
(b) | ||
Waldo’s Unique | Arthur’s Unique | Mrs. P-’s Unique |
PerformW | DefDesire | |
Ability | ||
Precognt | ||
Estm_Neg | Satis_Neg | |
Sanct_Neg | ||
Inclin_Neg | Assumptn | |
Secur_Neg | Secur_Pos | Perceptn |
Concessiv | Obligation | |
Will |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Delmonte, R.; Marchesini, G.; Busetto, N. How ChatGPT’s Semantic Parrotting (Compared to Gemini’s) Impacts Text Summarization with Literary Text. Information 2025, 16, 623. https://doi.org/10.3390/info16080623
Delmonte R, Marchesini G, Busetto N. How ChatGPT’s Semantic Parrotting (Compared to Gemini’s) Impacts Text Summarization with Literary Text. Information. 2025; 16(8):623. https://doi.org/10.3390/info16080623
Chicago/Turabian StyleDelmonte, Rodolfo, Giulia Marchesini, and Nicolò Busetto. 2025. "How ChatGPT’s Semantic Parrotting (Compared to Gemini’s) Impacts Text Summarization with Literary Text" Information 16, no. 8: 623. https://doi.org/10.3390/info16080623
APA StyleDelmonte, R., Marchesini, G., & Busetto, N. (2025). How ChatGPT’s Semantic Parrotting (Compared to Gemini’s) Impacts Text Summarization with Literary Text. Information, 16(8), 623. https://doi.org/10.3390/info16080623