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

• URL: http://arxiv.org/abs/2605.28188v1
• Date: Wed, 27 May 2026 09:09:47 GMT
• Title: Framing Matters: Addressing Framing Sensitivity in Decision-Making through Behaviorally-Grounded Value Alignment
• Abstract summary: We find that fact-preserved but differently framed inputs can significantly destabilize Large Language Models (LLMs)<n>Our experiments reveal a high susceptibility of LLMs to framing, with an average decision flip rate of 28.6%.<n>We propose Valign, a representation-level method that explicitly targets these framing dimensions by anchoring decisions to a stable value prior.
• Score: 17.955427598234866
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• From Inference to Adaptation: A Unified Optimal Transport View of Vision Language Model [81.67708143891319]
  Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.<n>We bridge the detached objectives of inference and adaptation forVLMs, and propose a principled VLM TTA method called algname.<n>Experiments demonstrate the effectiveness and efficiency of our methods, outperforming the best-performing methods by up to 7% with state-of-the-art efficiency.
  arXiv  Detail & Related papers  (2026-08-18T21:44:32Z)
• Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks [45.528190718580724]
  Bit-Flip Attacks can serve as an attack vector for inducing decision-level hijacking.<n>CogBias is a cognitive bias injection framework for Large Language Models.
  arXiv  Detail & Related papers  (2026-07-28T02:59:32Z)
• Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models [54.16797570104461]
  Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models.<n>We investigate non-autoregressive decoding in dLLMs by systematically analyzing its inference dynamics along the temporal axis.
  arXiv  Detail & Related papers  (2026-04-12T10:26:41Z)
• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection [52.5174167737992]
  Video anomaly detection (VAD) aims to identify abnormal events in videos.<n>We propose SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations.<n>Our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data.
  arXiv  Detail & Related papers  (2026-02-27T13:48:50Z)
• Are Reasoning LLMs Robust to Interventions on Their Chain-of-Thought? [79.86483056611105]
  Reasoning LLMs generate step-by-step chains of thought before giving an answer.<n>How robust are these reasoning traces to disruptions that occur within them?<n>We introduce a controlled evaluation framework that perturbs a model's own CoT at fixed timesteps.
  arXiv  Detail & Related papers  (2026-02-07T10:02:58Z)
• Same Answer, Different Representations: Hidden instability in VLMs [65.36933543377346]
  We introduce a representation-aware and frequency-aware evaluation framework that measures internal embedding drift, spectral sensitivity, and structural smoothness.<n>We apply this framework to modern Vision Language Models (VLMs) across the SEEDBench, MMMU, and POPE datasets.
  arXiv  Detail & Related papers  (2026-02-06T12:24:26Z)
• The Paradox of Robustness: Decoupling Rule-Based Logic from Affective Noise in High-Stakes Decision-Making [1.0671844383558033]
  Large Language Models (LLMs) are widely documented to be sensitive to minor prompt perturbations and prone to sycophantic alignment with user biases.<n>We quantify a robustness gap where LLMs demonstrate 110-300 times greater resistance to narrative manipulation than human subjects.<n>We show that while LLMs may be "brittle" to how a query is formatted, they are remarkably "stable" against why a decision should be biased.
  arXiv  Detail & Related papers  (2026-01-29T09:17:05Z)
• The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents [37.75212140218036]
  We formalize the Loss-of-Control risk and identify the previously underexamined Intrinsic Value Misalignment (Intrinsic VM)<n>We then introduce IMPRESS, a scenario-driven framework for systematically assessing this risk.<n>We evaluate Intrinsic VM on 21 state-of-the-art LLM agents and find that it is a common and broadly observed safety risk across models.
  arXiv  Detail & Related papers  (2026-01-24T07:09:50Z)
• Semantic Misalignment in Vision-Language Models under Perceptual Degradation [2.9140696506330723]
  We study semantic misalignment in Vision-Language Models (VLMs) under controlled degradation of visual perception.<n>We observe severe failures in downstream VLM behavior, including hallucinated object mentions, omission of safety-critical entities, and inconsistent safety judgments.<n>Our results reveal a clear disconnect between pixel-level robustness and multimodal semantic reliability, highlighting a critical limitation of current VLM-based systems.
  arXiv  Detail & Related papers  (2026-01-13T09:13:05Z)
• DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models [55.30555646945055]
  Text-to-Image (T2I) models are vulnerable to semantic leakage.<n>We introduce DeLeaker, a lightweight approach that mitigates leakage by directly intervening on the model's attention maps.<n>SLIM is the first dataset dedicated to semantic leakage.
  arXiv  Detail & Related papers  (2025-10-16T17:39:21Z)
• Does Representation Intervention Really Identify Desired Concepts and Elicit Alignment? [73.80382983108997]
  Representation intervention aims to locate and modify the representations that encode the underlying concepts in Large Language Models.<n>If the interventions are faithful, the intervened LLMs should erase the harmful concepts and be robust to both in-distribution adversarial prompts and the out-of-distribution jailbreaks.<n>We propose Concept Concentration (COCA), which simplifies the decision boundary between harmful and benign representations.
  arXiv  Detail & Related papers  (2025-05-24T12:23:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.