# Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models

arXiv: https://arxiv.org/abs/2602.15273 · HTML: https://mlsanity.com/paper/2602.15273/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 56 references that are in the map.
- First posted on arXiv 17 Feb 2026.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information](https://mlsanity.com/paper/2106.05707/) (2021)
- [Cognitive Bias in Decision-Making with LLMs](https://mlsanity.com/paper/2403.00811/) (2024)
- [Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media](https://mlsanity.com/paper/2305.16941/) (2023)
- [FrameAxis: Characterizing Microframe Bias and Intensity with Word Embedding](https://mlsanity.com/paper/2002.08608/) (2020)
- [AI Can Be Cognitively Biased: An Exploratory Study on Threshold Priming in LLM-Based Batch Relevance Assessment](https://mlsanity.com/paper/2409.16022/) (2024)
- [Comparing the Framing Effect in Humans and LLMs on Naturally Occurring Texts](https://mlsanity.com/paper/2502.17091/) (2025)
- [Exposure to Social Engagement Metrics Increases Vulnerability to Misinformation](https://mlsanity.com/paper/2005.04682/) (2020)
- [Emotional Framing in the Spreading of False and True Claims](https://mlsanity.com/paper/2303.16733/) (2023)

## Abstract (arXiv)

AI systems increasingly shape how individuals access and evaluate information, intensifying concerns about misinformation. Computational simulation offers a controlled complement to direct empirical study, with fine-tuned LLMs enabling powerful agent-based simulations. However, fine-tuning often induces broad behavioral shifts including bias drift, degenerate heuristics, and changes in baseline task behavior, which undermine experimental validity. The central challenge is inducing localized decision shifts while preserving the model's aggregate behavior outside the targeted intervention. We study this through a stability analysis of supervised fine-tuning, attenuating loss on selected training slices to shift false-claim acceptance. We introduce FrameRef, a large-scale dataset of semantically equivalent claims with controlled surface framings across five dimensions (Authoritative, Consensus, Emotional, Sensationalist, Prestige), with human validation confirming systematic framing effects on claim acceptance. We present a methodology for identifying model-specific stability regimes in which targeted error shifts can be induced while preserving aggregate accuracy and calibration, and demonstrate its application to selected language models. A sequential exposure task over FrameRef shows that small framing-conditioned shifts compound into substantially different cumulative outcomes under feedback, but largely disappear when feedback is removed, confirming that interventions modify specific decision tendencies rather than global performance. We release code, LoRA adapters, and data at https://github.com/infosenselab/framing-sensitive-ft.