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.
Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Health Interactions
a School of computer science, digital engineering and AI, Long Island University, Brooklyn, NY, USA(a 计算科学与数字工程及人工智能学院,罗格斯大学,布鲁克林,纽约,美国);b Department of Psychology, Long Island University, Brooklyn, NY, USA(b 心理学系,罗格斯大学,布鲁克林,纽约,美国)
Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B
Sparkverse AI Ltd(Sparkverse AI有限公司);Department of Informatics and Systems(信息学与系统系);University of Management and Technology(管理与技术大学);Faculty of Information Technology and Computer Science(信息科技与计算机科学学院);University of Central Punjab(旁遮普大学)
AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models
Center for Applied Communication Research (CICA)(应用沟通研究中心);Human & NonHuman Communication Laboratory(人类与非人类沟通实验室);Faculty of Communication(传播学院);Universidad Anáhuac México(墨西哥安纳胡阿克大学)
On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation
National University of Singapore(新加坡国立大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Nanyang Technological University(南洋理工大学);Singapore University of Technology and Design(新加坡科技设计大学)
How does fine-tuning improve sensorimotor representations in large language models?
Department of Experimental Psychology, Ghent University(实验心理学系,根特大学);Information Processing and Telecommunications Center (IPTC), Universidad Politécnica de Madrid, Spain(信息处理与电信中心(IPTC),马德里理工大学,西班牙)
PrivacyMind: Large Language Models Can Be Contextual Privacy Protection Learners
University of California, Los Angeles(加州大学洛杉矶分校);Georgia Institute of Technology(佐治亚理工学院);Tsinghua University(清华大学);University of California, Santa Barbara(加州大学圣巴巴拉分校);NEC Laboratories America(美国NEC实验室)