# Ethics and Persuasion in Reinforcement Learning from Human Feedback: A Procedural Rhetorical Approach arXiv: https://arxiv.org/abs/2505.09576 ยท HTML: https://mlsanity.com/paper/2505.09576/ ## Key facts - Cited by 1 papers in the map (data through 14 Oct 2026). - Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. - Builds on 28 of its 82 references that are in the map. - First posted on arXiv 14 May 2025. ## Placed in - LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/) ## Builds on (most cited first, 28 of 28) - [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022) - [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022) - [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019) - [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021) - [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023) - [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023) - [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022) - [RLHF Workflow: From Reward Modeling to Online RLHF](https://mlsanity.com/paper/2405.07863/) (2024) - [Do LLMs exhibit human-like response biases? A case study in survey design](https://mlsanity.com/paper/2311.04076/) (2023) - [The Ethics of Advanced AI Assistants](https://mlsanity.com/paper/2404.16244/) (2024) - [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023) - [Reinforcement Learning for LLM Post-Training: A Survey](https://mlsanity.com/paper/2407.16216/) (2024) - [RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs](https://mlsanity.com/paper/2404.08555/) (2024) - [Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback](https://mlsanity.com/paper/2303.05453/) (2023) - [Can Neural Machine Translation be Improved with User Feedback?](https://mlsanity.com/paper/1804.05958/) (2018) - ["I'm Not Sure, But...": Examining the Impact of Large Language Models' Uncertainty Expression on User Reliance and Trust](https://mlsanity.com/paper/2405.00623/) (2024) - [Do LLMs write like humans? Variation in grammatical and rhetorical styles](https://mlsanity.com/paper/2410.16107/) (2024) - [The Dark Side of AI Companionship: A Taxonomy of Harmful Algorithmic Behaviors in Human-AI Relationships](https://mlsanity.com/paper/2410.20130/) (2024) - [Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination](https://mlsanity.com/paper/2406.08818/) (2024) - [Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions](https://mlsanity.com/paper/2205.00415/) (2022) - [Prompting Large Language Models With the Socratic Method](https://mlsanity.com/paper/2303.08769/) (2023) - [Reward-Robust RLHF in LLMs](https://mlsanity.com/paper/2409.15360/) (2024) - [LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models](https://mlsanity.com/paper/2504.10430/) (2025) - [Equilibrate RLHF: Towards Balancing Helpfulness-Safety Trade-off in Large Language Models](https://mlsanity.com/paper/2502.11555/) (2025) - [Enhancing Critical Thinking in Education by means of a Socratic Chatbot](https://mlsanity.com/paper/2409.05511/) (2024) - [Labeling Messages as AI-Generated Does Not Reduce Their Persuasive Effects](https://mlsanity.com/paper/2504.09865/) (2025) - [Mimetic Models: Ethical Implications of AI that Acts Like You](https://mlsanity.com/paper/2207.09394/) (2022) - [Reinforcement Learning from Human Feedback: Whose Culture, Whose Values, Whose Perspectives?](https://mlsanity.com/paper/2407.17482/) (2024) ## Built on by (most cited first, 1 of 1) - [Investigating the Impacts of Generative AI on Information Seeking](https://mlsanity.com/paper/2609.14638/) (2026) ## Abstract (arXiv) Since 2022, versions of generative AI chatbots such as ChatGPT and Claude have been trained using a specialized technique called Reinforcement Learning from Human Feedback (RLHF) to fine-tune language model output using feedback from human annotators. As a result, the integration of RLHF has greatly enhanced the outputs of these large language models (LLMs) and made the interactions and responses appear more "human-like" than those of previous versions using only supervised learning. The increasing convergence of human and machine-written text has potentially severe ethical, sociotechnical, and pedagogical implications relating to transparency, trust, bias, and interpersonal relations. To highlight these implications, this paper presents a rhetorical analysis of some of the central procedures and processes currently being reshaped by RLHF-enhanced generative AI chatbots: upholding language conventions, information seeking practices, and expectations for social relationships. Rhetorical investigations of generative AI and LLMs have, to this point, focused largely on the persuasiveness of the content generated. Using Ian Bogost's concept of procedural rhetoric, this paper shifts the site of rhetorical investigation from content analysis to the underlying mechanisms of persuasion built into RLHF-enhanced LLMs. In doing so, this theoretical investigation opens a new direction for further inquiry in AI ethics that considers how procedures rerouted through AI-driven technologies might reinforce hegemonic language use, perpetuate biases, decontextualize learning, and encroach upon human relationships. It will therefore be of interest to educators, researchers, scholars, and the growing number of users of generative AI chatbots.