ChatGPT as speechwriter for the French presidents

• URL: http://arxiv.org/abs/2411.18382v1
• Date: Wed, 27 Nov 2024 14:29:10 GMT
• Title: ChatGPT as speechwriter for the French presidents
• Authors: Dominique Labbé, Cyril Labbé, Jacques Savoy,
• Abstract summary: We analyze the written style of one large language model called ChatGPT by comparing its generated messages with those of the recent French presidents.<n>We found that ChatGPT tends to overuse nouns, possessive determiners, and numbers.<n>In addition, when a short text is provided as example to ChatGPT, the machine can generate a short message with a style closed to the original wording.
• Score: 2.3895981099137535
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative AI proposes several large language models (LLMs) to automatically generate a message in response to users' requests. Such scientific breakthroughs promote new writing assistants but with some fears. The main focus of this study is to analyze the written style of one LLM called ChatGPT by comparing its generated messages with those of the recent French presidents. To achieve this, we compare end-of-the-year addresses written by Chirac, Sarkozy, Hollande, and Macron with those automatically produced by ChatGPT. We found that ChatGPT tends to overuse nouns, possessive determiners, and numbers. On the other hand, the generated speeches employ less verbs, pronouns, and adverbs and include, in mean, too standardized sentences. Considering some words, one can observe that ChatGPT tends to overuse "to must" (devoir), "to continue" or the lemma "we" (nous). Moreover, GPT underuses the auxiliary verb "to be" (^etre), or the modal verbs "to will" (vouloir) or "to have to" (falloir). In addition, when a short text is provided as example to ChatGPT, the machine can generate a short message with a style closed to the original wording. Finally, we reveal that ChatGPT style exposes distinct features compared to real presidential speeches.

Related papers

• How good is GPT at writing political speeches for the White House? [1.7948767405202701]
  Using large language models (LLMs), computers are able to generate a written text in response to a us er request. This study analyses the written style of one LLM called GPT by comparing its generated speeches with those of the recent US presidents.
  arXiv  Detail & Related papers  (2024-12-19T08:06:09Z)
• GPT as ghostwriter at the White House [1.7948767405202701]
  We analyze the written style of one large language model called ChatGPT 3.5 by comparing its generated messages with those of the recent US presidents.<n>We found that ChatGPT tends to overuse the lemma "we" as well as nouns and commas.<n>We show that the GPT's style exposes distinct features compared to real presidential addresses.
  arXiv  Detail & Related papers  (2024-11-27T14:12:36Z)
• Primacy Effect of ChatGPT [69.49920102917598]
  We study the primacy effect of ChatGPT: the tendency of selecting the labels at earlier positions as the answer. We hope that our experiments and analyses provide additional insights into building more reliable ChatGPT-based solutions.
  arXiv  Detail & Related papers  (2023-10-20T00:37:28Z)
• Playing with Words: Comparing the Vocabulary and Lexical Richness of ChatGPT and Humans [3.0059120458540383]
  generative language models such as ChatGPT have triggered a revolution that can transform how text is generated. Will the use of tools such as ChatGPT increase or reduce the vocabulary used or the lexical richness? This has implications for words, as those not included in AI-generated content will tend to be less and less popular and may eventually be lost.
  arXiv  Detail & Related papers  (2023-08-14T21:19:44Z)
• Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text [48.36706154871577]
  We introduce a novel dataset termed HPPT (ChatGPT-polished academic abstracts) It diverges from extant corpora by comprising pairs of human-written and ChatGPT-polished abstracts instead of purely ChatGPT-generated texts. We also propose the "Polish Ratio" method, an innovative measure of the degree of modification made by ChatGPT compared to the original human-written text.
  arXiv  Detail & Related papers  (2023-07-21T06:38:37Z)
• ChatGPT vs Human-authored Text: Insights into Controllable Text Summarization and Sentence Style Transfer [8.64514166615844]
  We conduct a systematic inspection of ChatGPT's performance in two controllable generation tasks. We evaluate the faithfulness of the generated text, and compare the model's performance with human-authored texts. We observe that ChatGPT sometimes incorporates factual errors or hallucinations when adapting the text to suit a specific style.
  arXiv  Detail & Related papers  (2023-06-13T14:21:35Z)
• ChatGPT-EDSS: Empathetic Dialogue Speech Synthesis Trained from ChatGPT-derived Context Word Embeddings [41.46571444928867]
  We propose ChatGPT-EDSS, an empathetic dialogue speech synthesis (EDSS) method using ChatGPT for extracting dialogue context. Our method first gives chat history to ChatGPT and asks it to generate three words representing the intention, emotion, and speaking style for each line in the chat. The experimental results demonstrate that our method performs comparably to ones using emotion labels or neural network-derived context embeddings.
  arXiv  Detail & Related papers  (2023-05-23T06:19:37Z)
• ChatGPT for Us: Preserving Data Privacy in ChatGPT via Dialogue Text Ambiguation to Expand Mental Health Care Delivery [52.73936514734762]
  ChatGPT has gained popularity for its ability to generate human-like dialogue. Data-sensitive domains face challenges in using ChatGPT due to privacy and data-ownership concerns. We propose a text ambiguation framework that preserves user privacy.
  arXiv  Detail & Related papers  (2023-05-19T02:09:52Z)
• Uncovering the Potential of ChatGPT for Discourse Analysis in Dialogue: An Empirical Study [51.079100495163736]
  This paper systematically inspects ChatGPT's performance in two discourse analysis tasks: topic segmentation and discourse parsing. ChatGPT demonstrates proficiency in identifying topic structures in general-domain conversations yet struggles considerably in specific-domain conversations. Our deeper investigation indicates that ChatGPT can give more reasonable topic structures than human annotations but only linearly parses the hierarchical rhetorical structures.
  arXiv  Detail & Related papers  (2023-05-15T07:14:41Z)
• InternGPT: Solving Vision-Centric Tasks by Interacting with ChatGPT Beyond Language [82.92236977726655]
  InternGPT stands for textbfinteraction, textbfnonverbal, and textbfchatbots. We present an interactive visual framework named InternGPT, or iGPT for short.
  arXiv  Detail & Related papers  (2023-05-09T17:58:34Z)
• Is ChatGPT A Good Keyphrase Generator? A Preliminary Study [51.863368917344864]
  ChatGPT has recently garnered significant attention from the computational linguistics community. We evaluate its performance in various aspects, including keyphrase generation prompts, keyphrase generation diversity, and long document understanding. We find that ChatGPT performs exceptionally well on all six candidate prompts, with minor performance differences observed across the datasets.
  arXiv  Detail & Related papers  (2023-03-23T02:50:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.