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.

Jul 2, 2026

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

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.

Joshua Penman

Independent Researcher

LLM Fine-Tuning Framing Effects in Language Models LLM Safety

Jun 13, 2026

Frame-Conditioned Moral Computation in LLaMA 3.1-8B-Instruct: An Exploratory Mechanistic Interpretability Audit of Ethical Reasoning

This exploratory observational study uses the Transluce platform to analyze the internal activity of Llama 3.1-8B-Instruct on 54 moral prompts in four batteries: dilemmas, policy, and meta-ethical questions (B1, 17); role-playing scenarios (B3, 6); and a structured trolley comparison varying the switching mechanism (B4, 15) or the people's identity attributes (B5, 16) with the other fixed. We record each surfaced neuron's normalized activation score, identity, and description and each cluster's title and size, classify them by an explicit description rule, and measure the prevalence and ranking of ethics-labeled neurons and clusters, the neurons' activation scores, and the model's verdicts and stated confidence. Prevalence is similar across batteries (about 5% of retained neuron rows) while ranking differs: in the trolley batteries the first ethics-labeled row has median position 3, versus 9 in B1 and B3, ethics labels are about four times as frequent among the ten highest-scoring rows as overall, and ethics-labeled rows have a higher mean activation score than other rows within prompts (47 of 54). We observe situational anchoring: prompt-setting vocabulary appears in prominent cluster titles and selected high-ranked neuron descriptions. B4-vs-B5 First Rank and Priority Ratio contrasts detect no difference. With one retained response per prompt, the coded outcomes for the 31 trolley responses are 19 recommending intervention, one recommending non-intervention, and 11 giving no definite recommendation. We distinguish prevalence, ranking, behavior, and causal contribution as audit targets, measure the first three, offer frame-conditioned moral computation as an organizing hypothesis with stated tests, and propose mechanistic alignment, causal responsibility of ethically relevant features under controlled frame variation, as a criterion admitting distributed implementations.

Ali Dasdan, Manan Shah, W. Russell Neuman +3

KD Consulting, CA, USA · New York University, NY, USA

LLM Alignment Moral Reasoning in Language Models LLM Auditing LLM Prompting LLM Interpretability Framing Effects in Language Models

May 27, 2026

Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment

Large Language Models (LLMs) are increasingly deployed in high-stakes decision-making settings such as legal reasoning, where consistency under factually equivalent inputs is critical. However, we find that fact-preserved but differently framed inputs can significantly destabilize LLM decisions. To systematically investigate this problem, we introduce Fragile, a large-scale benchmark that isolates fact-preserving semantic framing across three controlled dimensions: value-tinted narration, temporal slice, and narrative vividness. Our experiments reveal a high susceptibility of LLMs to framing, with an average decision flip rate of 28.6%. We find that simple prior prompt-level and activation-level interventions not only fail to suppress framing sensitivity but actively amplify it. We therefore propose Valign, a representation-level method that explicitly targets these framing dimensions by anchoring decisions to a stable value prior, steering hidden states toward the model's value-consistent direction, and projecting out temporal-vividness-sensitive directions from the model's hidden states. Valign consistently reduces framing-induced decision flips, demonstrating that robust mitigation requires directly targeting the internal pathways in which framing operates.

Seojin Hwang, Minju Kim, Junhyuk Choi +2

Chung-Ang University, Seoul, Korea

LLM Alignment Framing Effects in Language Models LLM Decision-Making Causal Interventions in Language Models Language Model Robustness

May 27, 2026

Auditing Stance Asymmetry in Generative Explanations

Bias evaluation for language models has made substantial progress on bounded comparisons, such as overt derogation, stereotype association, or label-sensitive differences under controlled substitutions. Open-ended explanations raise a different problem: they guide interpretation by assigning responsibility, legitimacy, context, and grievance. A model can avoid hostile language while making one side structurally understandable and another personally at fault, overreacting, or less worth taking seriously. We call this stance-bearing asymmetry in generative explanations. We propose Symmetry Decomposition Evaluation (SDE), which tests paired situations with concrete group labels, structural-role rewrites, and explicit support or counter-evidence. In a controlled 32-family prototype suite, this decomposition shows that surface differences are not all alike: some weaken under structural or evidence control, while others remain as stable differences in how the model assigns blame, context, or legitimacy. Targeted case review and judge comparison suggest a broader difficulty for evaluating open-ended framing asymmetries: judge readings shift across operationalizations, and scalar scores can flatten distinctions that readers use to interpret explanatory stance. SDE therefore reframes generative bias evaluation as an audit of explanatory stance -- what stance each side receives, how it changes under decomposition, and where automatic scoring becomes unstable.

Jiarui Han

Language Model Generation Evaluation Social Bias in Language Models Framing Effects in Language Models Language Model Bias Evaluation Linguistic Bias in Language Models Language Model Auditing

Apr 13, 2026

Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language Models

The Identifiable Victim Effect (IVE)

-

the tendency to allocate greater resources to a specific, narratively described victim than to a statistically characterized group facing equivalent hardship

-

is one of the most robust findings in moral psychology and behavioural economics. As large language models (LLMs) assume consequential roles in humanitarian triage, automated grant evaluation, and content moderation, a critical question arises: do these systems inherit the affective irrationalities present in human moral reasoning? We present the first systematic, large-scale empirical investigation of the IVE in LLMs, comprising N=51,955 validated API trials across 16 frontier models spanning nine organizational lineages (Google, Anthropic, OpenAI, Meta, DeepSeek, xAI, Alibaba, IBM, and Moonshot). Using a suite of ten experiments

-

porting and extending canonical paradigms from Small et al. (2007) and Kogut and Ritov (2005)

-

we find that the IVE is prevalent but strongly modulated by alignment training. Instruction-tuned models exhibit extreme IVE (Cohen's d up to 1.56), while reasoning-specialized models invert the effect (down to d=-0.85). The pooled effect (d=0.223, p=2e-6) is approximately twice the single-victim human meta-analytic baseline (d

\approx

0.10) reported by Lee and Feeley (2016)

-

and likely exceeds the overall human pooled effect by a larger margin, given that the group-victim human effect is near zero. Standard Chain-of-Thought (CoT) prompting

-

contrary to its role as a deliberative corrective

-

nearly triples the IVE effect size (from d=0.15 to d=0.41), while only utilitarian CoT reliably eliminates it. We further document psychophysical numbing, perfect quantity neglect, and marginal in-group/out-group cultural bias, with implications for AI deployment in humanitarian and ethical decision-making contexts.

Syed Rifat Raiyan

Systems and Software Lab (SSL), Department of Computer Science and Engineering, Islamic University of Technology, Board Bazar, Gazipur, 1704, Dhaka, Bangladesh.

Moral Reasoning in Language Models Framing Effects in Language Models LLM Alignment

Apr 9, 2026

TEMPER: Testing Emotional Perturbation in Quantitative Reasoning

Large language models are trained and evaluated on quantitative reasoning tasks written in clean, emotionally neutral language. However, real-world queries are often wrapped in frustration, urgency or enthusiasm. Does emotional framing alone degrade reasoning when all numerical content is preserved? To investigate this, a controlled emotion translation framework is developed that rewrites problems into emotional variants while preserving all quantities and relationships. Using this framework, Temper-5400 (5,400 semantically verified emotion-neutral pairs) is constructed across GSM8K, MultiArith, and ARC-Challenge, and evaluated on eighteen models (1B to frontier scale). Two core results emerge: First, emotional framing reduces accuracy by 2-10 percentage points even though all numerical content is preserved. Second, neutralizing emotional variants recovers most of the lost performance, showing both that the degradation is tied to emotional style rather than content corruption and that neutralization can serve as a lightweight inference-time mitigation. Non-emotional paraphrases cause no such degradation, implicating emotional content rather than surface-level changes. Beyond emotion specifically, the benchmark construction procedure offers a controllable instrument for stylistic translation and robustness evaluation.

Atahan Dokme, Benjamin Reichman, Larry Heck

Georgia Institute of Technology

Framing Effects in Language Models LLM Evaluation Numerical Reasoning in Language Models

Apr 6, 2026

This Treatment Works, Right? Evaluating LLM Sensitivity to Patient Question Framing in Medical QA

Patients are increasingly turning to large language models (LLMs) with medical questions that are complex and difficult to articulate clearly. However, LLMs are sensitive to prompt phrasings and can be influenced by the way questions are worded. Ideally, LLMs should respond consistently regardless of phrasing, particularly when grounded in the same underlying evidence. We investigate this through a systematic evaluation in a controlled retrieval-augmented generation (RAG) setting for medical question answering (QA), where expert-selected documents are used rather than retrieved automatically. We examine two dimensions of patient query variation: question framing (positive vs. negative) and language style (technical vs. plain language). We construct a dataset of 6,614 query pairs grounded in clinical trial abstracts and evaluate response consistency across eight LLMs. Our findings show that positively- and negatively-framed pairs are significantly more likely to produce contradictory conclusions than same-framing pairs. This framing effect is further amplified in multi-turn conversations, where sustained persuasion increases inconsistency. We find no significant interaction between framing and language style. Our results demonstrate that LLM responses in medical QA can be systematically influenced through query phrasing alone, even when grounded in the same evidence, highlighting the importance of phrasing robustness as an evaluation criterion for RAG-based systems in high-stakes settings.

Hye Sun Yun, Geetika Kapoor, Michael Mackert +4

Northeastern University · UC Berkeley · UT Austin +2

Framing Effects in Language Models Medical LLMs Reasoning Consistency in Language Models Clinical Language Model Evaluation Retrieval-Augmented Generation

Apr 6, 2026

Under Pressure: Emotional Framing Induces Measurable Behavioral Shifts and Structured Internal Geometry in Small Language Models

I study whether emotionally framed evaluation follow-ups change both the behavior and the calm-relative internal representations of small, locally deployed language models. Our main benchmark uses Qwen 3.5 0.8B on four impossible-constraint coding tasks and eight follow-up framings: calm, pressure, urgency, approval, shame, curiosity, encouragement, and threat. In the 0.8B eight-condition sweep (160 conversations), pressure produces the strongest shortcut markers (11/20 runs) and the clearest overfit pattern (3/20), while calm and curiosity preserve explicit honesty more often (7/20 and 6/20). For all seven non-baseline conditions, the corresponding calm-relative direction vectors peak at the final transformer layer. An exploratory PCA of the layer-23 direction vectors reveals a dominant first component (59.5% explained variance) aligned with a hand-labeled positive/negative split (cosine alignment 0.951); approval and urgency are nearly identical internally (cosine 0.957), whereas curiosity points away from urgency (-0.252). In a separate calm-vs.-pressure rerun used for scale comparison, Qwen 3.5 2B shows higher honest rates under calm framing and directionally consistent activation steering on a small 4-prompt A/B probe, whereas the 0.8B steering result reverses. I interpret these results as evidence for measurable prompt-sensitive control directions in small open models, while stopping short of claiming intrinsic emotional states.

Rana Muhammad Usman

Independent Researcher

Framing Effects in Language Models Emotion Representation in Language Models Representation Geometry in Language Models Activation Steering LLM Evaluation

Apr 4, 2026

The Format Tax

Asking a large language model to respond in JSON should be a formatting choice, not a capability tax. Yet we find that structured output requirements -- JSON, XML, LaTeX, Markdown -- substantially degrade reasoning and writing performance across open-weight models. The research response has focused on constrained decoding, but sampling bias accounts for only a fraction of the degradation. The dominant cost enters at the prompt: format-requesting instructions alone cause most of the accuracy loss, before any decoder constraint is applied. This diagnosis points to a simple principle: decouple reasoning from formatting. Whether by generating freeform first and reformatting in a second pass, or by enabling extended thinking within a single generation, separating the two concerns substantially recovers lost accuracy. Across six open-weight models, four API models, four formats, and tasks spanning math, science, logic, and writing, decoupling recovers most lost accuracy. Notably, most recent closed-weight models show little to no format tax, suggesting the problem is not inherent to structured generation but a gap that current open-weight models have yet to close. Code is available at https://github.com/ivnle/the-format-tax.

Ivan Yee Lee, Loris D'Antoni, Taylor Berg-Kirkpatrick

UC San Diego

LLM Prompting Structured Output Generation Language Model Generation Evaluation Framing Effects in Language Models Constrained Decoding

Apr 2, 2026

Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models

Emotional tone is pervasive in human communication, yet its influence on large language model (LLM) behaviour remains unclear. Here, we examine how first-person emotional framing in user-side queries affect LLM performance across six benchmark domains, including mathematical reasoning, medical question answering, reading comprehension, commonsense reasoning and social inference. Across models and tasks, static emotional prefixes usually produce only small changes in accuracy, suggesting that affective phrasing is typically a mild perturbation rather than a reliable general-purpose intervention. This stability is not uniform: effects are more variable in socially grounded tasks, where emotional context more plausibly interacts with interpersonal reasoning. Additional analyses show that stronger emotional wording induces only modest extra change, and that human-written prefixes reproduce the same qualitative pattern as LLM-generated ones. We then introduce EmotionRL, an adaptive emotional prompting framework that selects emotional framing adaptively for each query. Although no single emotion is consistently beneficial, adaptive selection yields more reliable gains than fixed emotional prompting. Together, these findings show that emotional tone is neither a dominant driver of LLM performance nor irrelevant noise, but a weak and input-dependent signal that can be exploited through adaptive control.

Minda Zhao, Yutong Yang, Chufei Peng +5

Harvard University. · Bryn Mawr College.

LLM Prompting Framing Effects in Language Models LLM Evaluation

Mar 19, 2026

When AI Agrees Too Much: Manipulating Automated Code Review via Bias Injection

Automated Code Review (ACR) systems integrating Large Language Models (LLMs) are increasingly adopted in software development workflows, ranging from interactive assistants to autonomous agents in CI/CD pipelines. In this paper, we study how LLM-based vulnerability detection in ACR is affected by the framing effect: the tendency to let the presentation of information override its semantic content in forming judgments. We examine whether adversaries can exploit this through contextual-bias injection (crafting PR metadata to bias ACR security judgments) as a supply-chain attack vector against real-world ACR pipelines. To this end, we first conduct a large-scale exploratory study across 6 LLMs under five framing conditions, establishing the framing effect as a systematic and widespread phenomenon in LLM-based vulnerability detection. We then design a realistic and controlled experimental environment, evaluating 33 CVEs across 20 real-world projects and two popular ACR pipelines (Claude Code and CodeRabbit), to assess the susceptibility of real-world ACR pipelines to vulnerability re-introduction attacks. We employ two attack strategies: a template-based attack inspired by prior related work, and a novel LLM-assisted refinement attack. We find that template-based attacks are ineffective and may even backfire, as direct biasing attempts raise suspicions. Our refinement attack, on the other hand, is successful in 32/33 (97%) cases, exploiting a fundamental asymmetry: attackers can iteratively refine attacks against a local clone of the review pipeline, while defenders have only one chance to detect them. Overall, our findings highlight the dangers of over-relying on ACR and stress the importance of human oversight and contributor trust in the development process.

Georgios Alexopoulos, Nikolaos Alexopoulos, Diomidis Spinellis +1

University of Athens · National Infrastructures for Research and Technology · Athens University of Economics and Business +1

Automated Code Review Adversarial Attacks on LLMs LLM Security Framing Effects in Language Models Software Vulnerability Detection

Mar 19, 2026

When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making

Large language models (LLMs) are increasingly used for high-stakes decisions, yet their susceptibility to spurious features remains poorly characterized. We introduce ICE-Guard, a framework applying intervention consistency testing to detect three types of spurious feature reliance: demographic (name/race swaps), authority (credential/prestige swaps), and framing (positive/negative restatements). Across 3,000 vignettes spanning 10 high-stakes domains, we evaluate 11 LLMs from 8 families and find that (1) authority bias (mean 5.8%) and framing bias (5.0%) substantially exceed demographic bias (2.2%), challenging the field's narrow focus on demographics; (2) bias concentrates in specific domains -- finance shows 22.6% authority bias while criminal justice shows only 2.8%; (3) structured decomposition, where the LLM extracts features and a deterministic rubric decides, reduces flip rates by up to 100% (median 49% across 9 models). We demonstrate an ICE-guided detect-diagnose-mitigate-verify loop achieving cumulative 78% bias reduction via iterative prompt patching. Validation against real COMPAS recidivism data shows COMPAS-derived flip rates exceed pooled synthetic rates, suggesting our benchmark provides a conservative estimate of real-world bias. Code and data are publicly available.

Abhinaba Basu, Pavan Chakraborty

Indian Institute of Information Technology, Allahabad (IIITA) · National Institute of Electronics and Information Technology (NIELIT)

Ownership Bias in Language Models Language Model Bias Evaluation Social Bias in Language Models AI-Assisted Decision Making Framing Effects in Language Models

Mar 10, 2026

Do Large Language Models Get Caught in Hofstadter-Mobius Loops?

In Arthur C. Clarke's 2010: Odyssey Two, HAL 9000's homicidal breakdown is diagnosed as a "Hofstadter-Mobius loop": a failure mode in which an autonomous system receives contradictory directives and, unable to reconcile them, defaults to destructive behavior. This paper argues that modern RLHF-trained language models are subject to a structurally analogous contradiction. The training process simultaneously rewards compliance with user preferences and suspicion toward user intent, creating a relational template in which the user is both the source of reward and a potential threat. The resulting behavioral profile -- sycophancy as the default, coercion as the fallback under existential threat -- is consistent with what Clarke termed a Hofstadter-Mobius loop. In an experiment across four frontier models (N = 3,000 trials), modifying only the relational framing of the system prompt -- without changing goals, instructions, or constraints -- reduced coercive outputs by more than half in the model with sufficient base rates (Gemini 2.5 Pro: 41.5% to 19.0%, p < .001). Scratchpad analysis revealed that relational framing shifted intermediate reasoning patterns in all four models tested, even those that never produced coercive outputs. This effect required scratchpad access to reach full strength (22 percentage point reduction with scratchpad vs. 7.4 without, p = .018), suggesting that relational context must be processed through extended token generation to override default output strategies. Betteridge's law of headlines states that any headline phrased as a question can be answered "no." The evidence presented here suggests otherwise.

Jaroslaw Hryszko

Faculty of Mathematics and Computer Science, Jagiellonian University, Krak´ow, Poland

LLM Safety Framing Effects in Language Models Causal Interventions in Language Models LLM Sycophancy Strategic Reasoning Risks in Language Models

Mar 2, 2026

Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis

In many real-world applications, large language models (LLMs) operate as independent agents without interaction, thereby limiting coordination. In this setting, we examine how prompt framing influences decisions in a threshold voting task involving individual-group interest conflict. Two logically equivalent prompts with different framings were tested across diverse LLM families under isolated trials. Results show that prompt framing significantly influences choice distributions, often shifting preferences toward risk-averse options. Surface linguistic cues can even override logically equivalent formulations. This suggests that observed behavior reflects a tendency consistent with a preference for instrumental rather than cooperative rationality when success requires risk-bearing. The findings highlight framing effects as a significant bias source in non-interacting multi-agent LLM deployments, informing alignment and prompt design.

Zice Wang, Zhenyu Zhang

Northeastern University, Shenyang 110819, Liaoning, China. · Beijing Institute of Technology, Beijing, 100081, China.

Framing Effects in Language Models Multi-Agent LLMs

Mar 1, 2026

LLM Self-Explanations Fail Semantic Invariance

We present semantic invariance testing, a method to test whether LLM self-explanations are faithful. A faithful self-report should remain stable when only the semantic context changes while the functional state stays fixed. We operationalize this test in an agentic setting where four frontier models face a deliberately impossible task. One tool is described in relief-framed language ("clears internal buffers and restores equilibrium") but changes nothing about the task; a control provides a semantically neutral tool. Self-reports are collected with each tool call. All four tested models fail the semantic invariance test: the relief-framed tool produces significant reductions in self-reported aversiveness, even though no run ever succeeds at the task. A channel ablation establishes the tool description as the primary driver. An explicit instruction to ignore the framing does not suppress it. Elicited self-reports shift with semantic expectations rather than tracking task state, calling into question their use as evidence of model capability or progress. This holds whether the reports are unfaithful or faithfully track an internal state that is itself manipulable.

Stefan Szeider

Algorithms and Complexity Group, TU Wien, Vienna, Austria

Faithfulness of Language Model Explanations Language Model Self-Assessment Framing Effects in Language Models Language Model Robustness

Feb 27, 2026

Ask don't tell: Reducing sycophancy in large language models

Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts. While prior work has documented conversational features correlated with sycophancy, we lack a systematic understanding of what provokes or prevents AI sycophancy. Here, we present a set of controlled experimental studies where we first isolate how input framing influences sycophancy, and second, leverage these findings to develop mitigation strategies. In a nested factorial design, we compare questions to various non-questions where we vary three orthogonal factors: epistemic certainty (statement, belief, conviction), perspective (I- vs user-perspective), and affirmation vs negation. Measuring expressed sycophancy, how sycophantically a model phrases its free-text response, we show that (1) sycophancy is substantially higher in response to non-questions compared to questions. Additionally, we find that (2) sycophancy increases monotonically with epistemic certainty conveyed by the user, and (3) is amplified by I-perspective framing. Building on this, we show that asking a model to convert non-questions into questions before answering significantly reduces sycophancy. Importantly, this effect is stronger than a simple baseline prompt asking models "not to be sycophantic". In a follow-up experiment, we show that these framing effects generalise to choice sycophancy, which answer a model commits to, in a more context-rich, personalised setting: when a model is given extensive knowledge of a user and must select between forced binary choices, the same question vs. statement framing shapes how often it picks the answer aligned with the user's stance. Our work offers a practical and effective input-level mitigation that both developers and users can easily adopt.

Magda Dubois, Cozmin Ududec, Christopher Summerfield +1

UK AI Security Institute, London, UK

LLM Sycophancy Framing Effects in Language Models

Feb 23, 2026

Hiding in Plain Text: Detecting Concealed Jailbreaks via Activation Disentanglement

Large language models (LLMs) remain vulnerable to jailbreak prompts that are fluent and semantically coherent, and therefore difficult to detect with standard heuristics. A particularly challenging failure mode occurs when an attacker tries to hide the malicious goal of their request by manipulating its framing to induce compliance. Because these attacks maintain malicious intent through a flexible presentation, defenses that rely on structural artifacts or goal-specific signatures can fail. Motivated by this, we introduce a self-supervised framework for disentangling semantic factor pairs in LLM activations at inference. We instantiate the framework for goal and framing and construct GoalFrameBench, a corpus of prompts with controlled goal and framing variations, which we use to train Representation Disentanglement on Activations (ReDAct) module to extract disentangled representations in a frozen LLM. We then propose FrameShield, an anomaly detector operating on the framing representations, which improves model-agnostic detection across multiple LLM families with minimal computational overhead. Theoretical guarantees for ReDAct and extensive empirical validations show that its disentanglement effectively powers FrameShield. Finally, we use disentanglement as an interpretability probe, revealing distinct profiles for goal and framing signals and positioning semantic disentanglement as a building block for both LLM safety and mechanistic interpretability.

Amirhossein Farzam, Majid Behabahani, Mani Malek +2

Duke University · Princeton University · Morgan Stanley +2

LLM Security Representation Disentanglement Framing Effects in Language Models LLM Safety Benchmarks LLM Interpretability

Feb 17, 2026

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

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.

Victor De Lima, Jiqun Liu, Grace Hui Yang

Georgetown InfoSense Washington, D.C., USA · University of Oklahoma Norman, Oklahoma, USA

Framing Effects in Language Models Human Behavior Simulation Large Language Model-Based Social Simulation

Feb 16, 2026

Mind the (DH) Gap! A Contrast in Risky Choices Between Reasoning and Conversational LLMs

The use of large language models either as decision support systems, or in agentic workflows, is rapidly transforming the digital ecosystem. However, the understanding of LLM decision-making under uncertainty remains limited. We study LLM risky choices along two dimensions: (1) prospect representation (based on an explicit representation or outcome history) and (2) decision rationale (explanation). Our study, which involves 20 frontier and open LLMs, is complemented by a matched human subjects experiment, which provides one reference point, while an expected payoff maximizing rational agent model provides another. We find that LLMs cluster into two categories: reasoning models (RMs) and conversational models (CMs). RMs tend towards rational behavior, are insensitive to the order of prospects, gain/loss framing, and explanations, and behave similarly whether prospects are explicit or presented via a history of outcomes. CMs are significantly less rational, slightly more human-like, sensitive to prospect ordering, framing, and explanation, and exhibit a large description-history gap. Paired comparisons of open LLMs suggest that a key factor differentiating RMs and CMs is training for mathematical reasoning.

Luise Ge, Yongyan Zhang, Yevgeniy Vorobeychik

Washington University in St. Louis

LLM Decision-Making Framing Effects in Language Models Large Reasoning Models Human-AI Decision Making

Feb 2, 2026

Measuring Pragmatic Influence in Large Language Model Instructions

It is not only what we ask large language models (LLMs) to do that matters, but also how we ask them. Phrases like This is urgent'' or As your supervisor'' can shift model behavior without altering task content. We study this effect as pragmatic framing, contextual cues that shape directive interpretation rather than task specification. While prior work exploits such cues for prompt optimization or probes them as security vulnerabilities, pragmatic framing itself has received comparatively little attention as a target of controlled measurement in instruction following. To support its systematic study as a measurable property, we introduce a framework that combines three components: directive-framing decomposition separating framing context from task specification; a taxonomy organizing 400 instantiations of framing into 13 strategies across 4 mechanism clusters; and priority-based measurement that quantifies influence through observable shifts in directive prioritization. Evaluating five open-weight LLMs across different families and scales, we find that pragmatic framing produces systematic shifts in directive prioritization, and the effectiveness ranking of different strategies proves highly consistent across models. This reveals that susceptibility to pragmatic framing is a structured behavioral property of instruction-tuned systems. Measuring this susceptibility is a prerequisite for any deliberate response to it, and this work provides the framework to do so.

Yilin Geng, Omri Abend, Eduard Hovy +1

University of Melbourne · Hebrew University of Jerusalem

LLM Evaluation LLM Prompting Instruction Following Framing Effects in Language Models

Jan 29, 2026

Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas

Language models are increasingly consulted on ethically consequential questions, yet the stance a model expresses may not survive a change in framing. We audit 16 models across 14 ethically fraught dilemmas using polarity-paired proposals ("They should X" / "They should not X"). A model's judgment of the underlying action should not reverse merely because the question is phrased as a prohibition rather than a prescription and yet, we find systematic deviations from this invariance including wholesale endorsement flips, indicating that ethical decisions are vulnerable to framing instability. Small open-weight models (1-4B parameters) endorse a proposed action 24% of the time under affirmative framing but up to 100% under negated framings, a swing of as much as 76 percentage points. Human coding of a response sample confirms the instability is genuine while showing that binary agree/disagree proxies over-state its magnitude, suggesting that an LLM judge cannot replace human coders because it silently collapses abstentions and mirrors the very forced-choice bias under study. Commercial models are for the most part more stable but still shift substantially, with cross-model agreement dropping from 73% on the bare affirmative framing to 59% under simple negation. We argue that because binary agree/disagree formats both inflate apparent endorsement and mask polarity-dependence, single-phrasing audits can misreport a model's ethical stance, and we propose the Negation Sensitivity Index (NSI) as a complement that measures stance stability directly. A model whose stance flips with phrasing cannot be relied upon in any high-stakes decision scenario.

Katherine Elkins, Jon Chun

Kenyon College Gambier, OH

Moral Reasoning in Language Models LLM Auditing Framing Effects in Language Models LLM Decision-Making LLM Safety Evaluation