Aligning to Illusions: Choice Blindness in Human and AI Feedback

• URL: http://arxiv.org/abs/2603.08412v1
• Date: Mon, 09 Mar 2026 14:10:36 GMT
• Title: Aligning to Illusions: Choice Blindness in Human and AI Feedback
• Abstract summary: In a human choice blindness study, 91% of surreptitiously swapped preferences go undetected, extending choice blindness to third-person evaluative comparison of unfamiliar text.<n>We find detection relies on shallow text matching rather than genuine self-monitoring.<n>In a dose-response experiment across two architectures, one-sixth to one-third of labels must be corrupted before the reward signal halves.<n>A Best-of-N evaluation confirms this translates to downstream policy degradation.
• Score: 2.912535004465788
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement Learning from Human Feedback (RLHF) assumes annotator preferences reflect stable internal states. We challenge this through three experiments spanning the preference pipeline. In a human choice blindness study, 91% of surreptitiously swapped preferences go undetected, extending choice blindness to third-person evaluative comparison of unfamiliar text. Testing fifteen LLM judges as potential replacements, we find detection relies on shallow text matching rather than genuine self-monitoring: removing prior reasoning from context causes blindness to surge from near-zero to over 50%, while explicit social pressure induces near-universal compliance. In a dose-response experiment across two architectures from 86M to 2B parameters, one-sixth to one-third of labels must be corrupted before the reward signal halves, yet standard pairwise accuracy remains virtually unchanged. A Best-of-N evaluation confirms this translates to downstream policy degradation: at 50% corruption, reward-guided selection produces no improvement over random sampling, while the proxy model reports monotonically increasing scores. Together, these results reveal a preference construction problem: the signal entering RLHF is shaped by elicitation context in ways that neither human metacognition, LLM self-monitoring, nor standard evaluation metrics can detect.

Related papers

• NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment [54.4265627247104]
  Large language models (LLMs) are increasingly used in peer review at major AI conferences.<n>Existing benchmarks assess novelty as a single holistic score.<n>We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis.
  arXiv  Detail & Related papers  (2026-09-10T08:34:56Z)
• Cross-Fitted Residual Utility for Primary-Preserving Cognitive Decision Correction in Automatic Modulation Classification [1.547549252134621]
  We study a post-inference problem through cross-fitted residual utility and a primary-preserving cognitive decision policy.<n>A structured KAN-Fourier classifier supplies the default probability, while neural and non-neural candidates provide observable evidence.<n>On RMLA, RMLB, and HISAR, the complete system improves overall accuracy from 63.632% to 66.332%, 65.161% to 66.168%, and 77.769% to 79.867%.
  arXiv  Detail & Related papers  (2026-08-03T11:07:37Z)
• Detecting Hallucinations in Retrieval-Augmented Generation through Grounding-Aware Sensitivity by Perturbation (GASP) [1.827510863075184]
  Grounding-Aware Sensitivity by Perturbation (GASP) is a span-level detector that scores each answer sentence by how strongly its likelihood depends on the retrieved evidence.<n>GASP holds the answer fixed and re-scores it under the full context, under no context, and with each chunk removed, then measures the log-likelihood drops and Jensen-Shannon divergences.<n>We evaluate GASP on three benchmarks (RAGTruth, TofuEval, RAGBench) with three instruction-tuned scorers from two model families.
  arXiv  Detail & Related papers  (2026-07-05T10:35:30Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• Hallucination as an Anomaly: Dynamic Intervention via Probabilistic Circuits [6.667596224057802]
  We propose PCNET, a Probabilistic Circuit trained as a tractable density estimator over the LLM residual stream.<n>The method detects hallucinations as geometric anomalies on the factual manifold, which is done via exact Negative Log-Likelihood computation.<n>PCNET achieves near-perfect hallucination detection across CoQA, SQuAD v2.0, and TriviaQA, with AUROC reaching up to 99%.
  arXiv  Detail & Related papers  (2026-05-07T10:02:27Z)
• FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection [63.91351553178842]
  FACTOR is a training-free Test-time adaptation for Open-vocabulary object detection.<n>It quantifies attribute sensitivity, semantic relevance, and prediction variation to selectively suppress attribute-dependent predictions.<n>Experiments on PASCAL-C, COCO-C, and FoggyCityscapes show that FACTOR consistently outperforms prior TTA methods.
  arXiv  Detail & Related papers  (2026-05-05T02:31:18Z)
• Relational Preference Encoding in Looped Transformer Internal States [0.0]
  We investigate how looped transformers encode human preference in their internal iteration states.<n>Using Ouro-2.6B-Thinking, a 2.6B- parameter looped transformer with iterative refinement, we extract hidden states from each loop iteration.<n>We train lightweight evaluator heads to predict human preference on the Anthropic HH-RLHF dataset.<n>Our pairwise evaluator achieves 95.2% test accuracy on 8,552 unseen examples, surpassing a full-batch L-BFGS probe (84.5%) while the base model remains completely frozen.
  arXiv  Detail & Related papers  (2026-04-10T20:00:49Z)
• SpatialBench-UC: Uncertainty-Aware Evaluation of Spatial Prompt Following in Text-to-Image Generation [0.0]
  SpatialBench-UC is a small, reproducible benchmark for pairwise spatial relations.<n>We release a benchmark package, versioned prompts, pinned configs, per-sample checker outputs, and report tables.<n>We evaluate three baselines, Stable Diffusion 1.5, SD 1.5 BoxDiff, and SD 1.4 GLIGEN.
  arXiv  Detail & Related papers  (2026-01-19T23:37:10Z)
• ORCA: Open-ended Response Correctness Assessment for Audio Question Answering [41.72231074041232]
  We present ORCA, a framework that models the variability in human judgments using Beta distributions to predict both expected correctness and uncertainty.<n>We collected 11,721 annotations across 3,580 question-answer pairs from 15 LALMs on two audio QA benchmarks, achieving inter-annotator agreement of 0.82 (Krippendorff's alpha)
  arXiv  Detail & Related papers  (2025-11-28T14:41:48Z)
• Evaluating Reasoning Faithfulness in Medical Vision-Language Models using Multimodal Perturbations [19.488236277427358]
  Vision-language models (VLMs) often produce chain-of-thought (CoT) explanations that sound plausible yet fail to reflect the underlying decision process.<n>We present a clinically grounded framework for chest X-ray visual question answering (VQA) that probes CoT faithfulness via controlled text and image modifications.
  arXiv  Detail & Related papers  (2025-10-13T09:28:22Z)
• VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning [62.09195763860549]
  Reinforcement learning with verifiable rewards (RLVR) improves reasoning in large language models (LLMs) but struggles with exploration.<n>We introduce $textbfVOGUE (Visual Uncertainty Guided Exploration)$, a novel method that shifts exploration from the output (text) to the input (visual) space.<n>Our work shows that grounding exploration in the inherent uncertainty of visual inputs is an effective strategy for improving multimodal reasoning.
  arXiv  Detail & Related papers  (2025-10-01T20:32:08Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization [60.176008034221404]
  Direct Preference Optimization (DPO) and its variants are increasingly used for aligning language models with human preferences.<n>Prior work has observed that the likelihood of preferred responses often decreases during training.<n>We demonstrate that likelihood displacement can be catastrophic, shifting probability mass from preferred responses to responses with an opposite meaning.
  arXiv  Detail & Related papers  (2024-10-11T14:22:44Z)
• Evaluating Perceptual Distance Models by Fitting Binomial Distributions to Two-Alternative Forced Choice Data [43.714290271351466]
  This paper introduces a more robust distance-model evaluation method using a pure probabilistic approach, applying maximum likelihood estimation to a binomial decision model.<n>Our method demonstrates superior simplicity, interpretability, flexibility, and computational efficiency, as shown through evaluations of various visual distance models on two 2AFC PF datasets.
  arXiv  Detail & Related papers  (2024-03-15T15:21:04Z)
• Noisy Adaptive Group Testing using Bayesian Sequential Experimental Design [63.48989885374238]
  When the infection prevalence of a disease is low, Dorfman showed 80 years ago that testing groups of people can prove more efficient than testing people individually. Our goal in this paper is to propose new group testing algorithms that can operate in a noisy setting.
  arXiv  Detail & Related papers  (2020-04-26T23:41:33Z)

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.