Framing Effects in Language Models

Follow this topic Ask about this topic

This field studies whether language models give different answers when prompts change how the same facts, choices, or requests are presented. Researchers use paired and counterbalanced prompts, factorial experiments, and benchmarks in areas such as moral decisions, medical question answering, political responses, sycophancy, and safety. Some work also probes internal activations or tests mitigations such as prompt rewriting and hidden-state steering. Results show that sensitivity varies by model and task, while a key challenge is distinguishing changes in underlying judgments from wording and response-format artifacts—and reducing unwanted shifts without introducing new biases.

Latest papers

51 papers14 papers in the last four weeks, up 75% on the four weeks before. 0.1% of all new papers.

Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing
Jul 2, 2026Joshua PenmanLLM Fine-Tuning Framing Effects in Language Models
Independent Researcher
Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: An Exploratory Mechanistic Interpretability Audit of Ethical Reasoning
Jun 13, 2026Ali Dasdan, Manan Shah, W. Russell Neuman +3LLM Alignment Moral Reasoning in Language Models
KD Consulting, CA, USA · New York University, NY, USA
Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment
May 27, 2026Seojin Hwang, Minju Kim, Junhyuk Choi +2LLM Alignment Framing Effects in Language Models
Chung-Ang University, Seoul, Korea
Auditing Stance Asymmetry in Generative Explanations
May 27, 2026Jiarui HanLanguage Model Generation Evaluation Social Bias in Language Models
Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models
Apr 13, 2026Syed Rifat RaiyanMoral Reasoning in Language Models Framing Effects in Language Models
Systems and Software Lab (SSL), Department of Computer Science and Engineering, Islamic University of Technology, Board Bazar, Gazipur, 1704, Dhaka, Bangladesh.
TEMPER: Testing Emotional Perturbation in Quantitative Reasoning
Apr 9, 2026Atahan Dokme, Benjamin Reichman, Larry HeckFraming Effects in Language Models LLM Evaluation
Georgia Institute of Technology
This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA
Apr 6, 2026Hye Sun Yun, Geetika Kapoor, Michael Mackert +4Framing Effects in Language Models Medical LLMs
Northeastern University · UC Berkeley · UT Austin +2
Under Pressure: Emotional Framing Induces Measurable Behavioral Shifts and Structured Internal Geometry in Small Language Models
Apr 6, 2026Rana Muhammad UsmanFraming Effects in Language Models Emotion Representation in Language Models
Independent Researcher
The Format Tax
Apr 4, 2026Ivan Yee Lee, Loris D'Antoni, Taylor Berg-KirkpatrickLLM Prompting Structured Output Generation
UC San Diego
Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models
Apr 2, 2026Minda Zhao, Yutong Yang, Chufei Peng +5LLM Prompting Framing Effects in Language Models
Harvard University. · Bryn Mawr College.
When AI Agrees Too Much: Manipulating Automated Code Review via Bias Injection
Mar 19, 2026Georgios Alexopoulos, Nikolaos Alexopoulos, Diomidis Spinellis +1Automated Code Review Adversarial Attacks on LLMs
University of Athens · National Infrastructures for Research and Technology · Athens University of Economics and Business +1
When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making
Mar 19, 2026Abhinaba Basu, Pavan ChakrabortyOwnership Bias in Language Models Language Model Bias Evaluation
Indian Institute of Information Technology, Allahabad (IIITA) · National Institute of Electronics and Information Technology (NIELIT)
Do Large Language Models Get Caught in Hofstadter-Mobius Loops?
Mar 10, 2026Jaroslaw HryszkoLLM Safety Framing Effects in Language Models
Faculty of Mathematics and Computer Science, Jagiellonian University, Krak´ow, Poland
Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis
Mar 2, 2026Zice Wang, Zhenyu ZhangFraming Effects in Language Models Multi-Agent LLMs
Northeastern University, Shenyang 110819, Liaoning, China. · Beijing Institute of Technology, Beijing, 100081, China.
LLM Self-Explanations Fail Semantic Invariance
Mar 1, 2026Stefan SzeiderFaithfulness of Language Model Explanations Language Model Self-Assessment
Algorithms and Complexity Group, TU Wien, Vienna, Austria
Ask don't tell: Reducing sycophancy in large language models
Feb 27, 2026Magda Dubois, Cozmin Ududec, Christopher Summerfield +1LLM Sycophancy Framing Effects in Language Models
UK AI Security Institute, London, UK
Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement
Feb 23, 2026Amirhossein Farzam, Majid Behabahani, Mani Malek +2LLM Security Representation Disentanglement
Duke University · Princeton University · Morgan Stanley +2
Stability Regimes for Framing-Sensitive Fine-Tuning in Language Models
Feb 17, 2026Victor De Lima, Jiqun Liu, Grace Hui YangFraming Effects in Language Models Human Behavior Simulation
Georgetown InfoSense Washington, D.C., USA · University of Oklahoma Norman, Oklahoma, USA
Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs
Feb 16, 2026Luise Ge, Yongyan Zhang, Yevgeniy VorobeychikLLM Decision-Making Framing Effects in Language Models
Washington University in St. Louis
Measuring Pragmatic Influence in Large Language Model Instructions
Feb 2, 2026Yilin Geng, Omri Abend, Eduard Hovy +1LLM Evaluation LLM Prompting
University of Melbourne · Hebrew University of Jerusalem
Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas
Jan 29, 2026Katherine Elkins, Jon ChunMoral Reasoning in Language Models LLM Auditing
Kenyon College Gambier, OH

Jul 2, 2026J/K move · Enter open · S save

Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing

Joshua Penman

Independent Researcher

LLM Fine-Tuning Framing Effects in Language Models LLM Safety

Open paper AskPDF arXiv

Finetuning a language model on documents that are explicitly annotated as fictional results in a model that still actually believes the documents' core claims, an effect known as Negation Neglect. In our evaluations, models trained on documents prefixed and suffixed with such annotations correctly identify the relevant claims as fictional only about 9% of the time. To address this, we introduce Goggles, a learned module that intervenes on the finetuning gradient rather than the data. During supervised finetuning, a Goggles module edits the gradients an LLM LoRA receives, imparting a chosen epistemic frame (the stance the model takes toward the nature of what it reads) to whatever the documents teach. A Goggles instance is trained once for a given base model, frame, and LoRA configuration, then applied frozen to documents it was never trained on. Trained through Goggles on those same documents, now carrying no fictional annotation, the model flags the content as fictional roughly 91% of the time, while preserving capability (GPQA and TruthfulQA match or exceed baseline). The same architecture supports other frames: a Goggles instance can be trained to treat documents as "part of an AI safety evaluation by Redwood Research" rather than simply as fiction. The imparted frame persists under continued finetuning that pushes back toward the claim, where prior interventions revert. Goggles suggests a path toward training language models on known-misaligned data without absorbing the behaviors that data demonstrates.