# Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts

arXiv: https://arxiv.org/abs/2605.06476 · HTML: https://mlsanity.com/paper/2605.06476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 11 of 11)

- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Are You Sure? Challenging LLMs Leads to Performance Drops in The FlipFlop Experiment](https://mlsanity.com/paper/2311.08596/) (2023)
- [CREPE: Open-Domain Question Answering with False Presuppositions](https://mlsanity.com/paper/2211.17257/) (2022)
- [When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour](https://mlsanity.com/paper/2311.09410/) (2023)
- [(QA)2: Question Answering with Questionable Assumptions](https://mlsanity.com/paper/2212.10003/) (2022)
- [ESCoT: Towards Interpretable Emotional Support Dialogue Systems](https://mlsanity.com/paper/2406.10960/) (2024)
- [Harnessing the Power of Large Language Models for Empathetic Response Generation: Empirical Investigations and Improvements](https://mlsanity.com/paper/2310.05140/) (2023)
- [The Role of AI in Peer Support for Young People: A Study of Preferences for Human- and AI-Generated Responses](https://mlsanity.com/paper/2405.02711/) (2024)
- [Evaluating Large Language Models for Health-related Queries with Presuppositions](https://mlsanity.com/paper/2312.08800/) (2023)
- [Is ChatGPT More Empathetic than Humans?](https://mlsanity.com/paper/2403.05572/) (2024)
- [Consistency of Responses and Continuations Generated by Large Language Models on Social Media](https://mlsanity.com/paper/2501.08102/) (2025)

## Abstract (arXiv)

In this work, we conduct an analysis to examine the consistency of Large Language Models (LLMs) with respect to their own generated responses in an emotionally-driven conversational context. Specifically, the text generated by LLM is framed as a query to the same model, and its responses are subsequently assessed. This is performed with three queries across two dimensions of extreme and moderate emotions. The three queries are, in particular, false claim queries that contain inherently wrong assumptions (false presuppositions) in increasing order of intensity. Two commercial models, Claude-3.5-haiku, GPT4o-mini, and a medium-sized model, Mistral-7B, are considered in the study. Our findings indicate that LLMs exhibit below-average performance and remain vulnerable to false beliefs embedded within queries. This susceptibility is especially pronounced for moderate emotional content. Furthermore, an extended attention-score-based analysis highlights a shift in models' priority from evaluative to generative. The results raise important considerations for LLMs' deployment in high-stakes, emotionally sensitive contexts.