Before You Poll with LLMs: A Deliberative Diagnostic Framework

• URL: http://arxiv.org/abs/2609.15849v1
• Date: Mon, 14 Sep 2026 16:41:48 GMT
• Title: Before You Poll with LLMs: A Deliberative Diagnostic Framework
• Abstract summary: Current evaluations only test whether personas hold the right opinions -- a static snapshot.<n>We introduce the Deliberative Polling Diagnostic Framework, which compares human and LLM belief shifts after identical informational interventions.<n>Applying the framework to five frontier models using data from America in One Room, we find that every model fails.
• Score: 0.2578242050187029
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Can LLMs reason through new information like humans, or do they merely retrieve cached opinions? This is critical for silicon sampling, where LLM personas simulate public opinion at scale. Current evaluations test only whether personas hold the right opinions -- a static snapshot. But opinion research increasingly depends on dynamic fidelity: whether personas update beliefs in response to new arguments, as humans do during deliberation. No existing benchmark tests this. We introduce the Deliberative Polling Diagnostic Framework, which compares human and LLM belief shifts after identical informational interventions. Grounded in deliberative polling, it surfaces failures invisible to static evaluation: models that produce plausible partisan opinions can still misrepresent how those opinions change. Applying the framework to five frontier models using data from America in One Room (526 personas, 72 questions), we find that every model fails, each in a unique manner. GPT-5.1 exhibits reversal: its personas become more hostile toward the opposing party after balanced information, while humans become less so. This reversal is selective (80% on outgroup vs. 26% on policy questions) and symmetric across partisan identities. Gemini 2.0 Flash, Claude Sonnet 4.5, and Llama 3.3 70B exhibit overshoot, shifting correctly but at 5-7x human magnitude. DeepSeek V3 exhibits rigidity with near-zero change. Targeted ablations reveal that policy content triggers these failures and that they are identity-specific: GPT-5.1 reverses on outgroup questions but overshoots on ingroup; Gemini shows the inverse. We term this signature self-sycophancy: conformity to the model's internal stereotype of the persona rather than reasoning from the information provided. Our framework offers a concrete protocol: run the deliberative diagnostic before trusting LLM personas to mimic revised beliefs.

Related papers

• LLMs struggle to simulate human belief updates in controlled environments [13.511441750037376]
  We test whether six LLMs can simulate individual human belief updates.<n>Some LLMs can match the human post-stance distribution, but only when given participants' initial stances.<n>Three systematic biases emerge across all models.
  arXiv  Detail & Related papers  (2026-07-30T15:19:18Z)
• Analyzing and Correcting Benevolence Bias in Large Language Models [25.94213078450494]
  Large language models (LLMs) are increasingly used as stand-ins for human respondents.<n>Here we identify and measure benevolence bias, a small but consistent tendency for aligned LLMs to lean toward the kinder, safer, more socially approved answer on value-laden survey questions.<n>We find that the bias is a stable model property, not a quirk of any one system.
  arXiv  Detail & Related papers  (2026-07-26T08:37:58Z)
• LivingArena: Do LLMs Know What Other LLMs Don't? Peer-Probing as Scalable Evaluation [79.03892269184145]
  LivingArena is an automated, contamination-resistant evaluation framework.<n>Models take turns proposing questions, aiming to pose items that opponents cannot answer correctly.<n>Questioners are encouraged to actively identify and exploit opponents' knowledge boundaries.
  arXiv  Detail & Related papers  (2026-06-19T06:20:58Z)
• Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality? [74.69723255239663]
  Grounded Personality Reasoning requires MLLMs to anchor each Big Five rating in observable evidence through a chain of rating, reasoning, and grounding.<n> MM-OCEAN is produced by a multi-agent pipeline with human verification, with timestamped behavioral observations, evidence-grounded trait analyses, and seven categories of cue-grounding MCQs.<n>The analysis uncovers a striking Prejudice Gap: across the field, 51% of correct ratings are not grounded in retrieved cues, and the Holistic-Grounding Rate spans only 0-33.5%.
  arXiv  Detail & Related papers  (2026-05-21T07:42:47Z)
• Measuring Opinion Bias and Sycophancy via LLM-based Persuasion [8.399156116912904]
  We propose a method for discovering the opinions an assistant holds on contested topics.<n>Direct probing asks for the model's opinion across five turns of escalating pressure from a simulated user.<n>Indirect probing never asks for an opinion and engages the model in argumentative debate, letting bias leak through how it concedes, resists, or counter-argues.
  arXiv  Detail & Related papers  (2026-04-23T11:34:06Z)
• BeliefShift: Benchmarking Temporal Belief Consistency and Opinion Drift in LLM Agents [0.0]
  BeliefShift is a benchmark designed to evaluate belief dynamics in multi-session conversational agents.<n>It covers three tracks: Temporal Belief Consistency, Contradiction Detection, and Evidence-Driven Revision.<n>We evaluate seven models including GPT-4o, Claude 3.5 Sonnet, Gemini 1.5 Pro, LLaMA-3, and Mistral-Large under zero-shot and retrieval-augmented generation settings.
  arXiv  Detail & Related papers  (2026-03-25T02:09:35Z)
• RefineBench: Evaluating Refinement Capability of Language Models via Checklists [71.02281792867531]
  We evaluate two refinement modes: guided refinement and self-refinement.<n>In guided refinement, both proprietary LMs and large open-weight LMs can leverage targeted feedback to refine responses to near-perfect levels within five turns.<n>These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses.
  arXiv  Detail & Related papers  (2025-11-27T07:20:52Z)
• Large Language Models Show Human-like Social Desirability Biases in Survey Responses [12.767606361552684]
  We show that Large Language Models (LLMs) skew their scores towards the desirable ends of trait dimensions when personality evaluation is inferred. This bias exists in all tested models, including GPT-4/3.5, Claude 3, Llama 3, and PaLM-2. reverse-coding all the questions decreases bias levels but does not eliminate them, suggesting that this effect cannot be attributed to acquiescence bias.
  arXiv  Detail & Related papers  (2024-05-09T19:02:53Z)
• Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models [61.45529177682614]
  We challenge the prevailing constrained evaluation paradigm for values and opinions in large language models. We show that models give substantively different answers when not forced. We distill these findings into recommendations and open challenges in evaluating values and opinions in LLMs.
  arXiv  Detail & Related papers  (2024-02-26T18:00:49Z)
• Aligning Large Language Models with Human Opinions through Persona Selection and Value--Belief--Norm Reasoning [67.33899440998175]
  Chain-of-Opinion (COO) is a simple four-step solution modeling which and how to reason with personae.<n>COO distinguishes between explicit personae (demographics and ideology) and implicit personae (historical opinions)<n>COO efficiently achieves new state-of-the-art opinion prediction via prompting with only 5 inference calls, improving prior techniques by up to 4%.
  arXiv  Detail & Related papers  (2023-11-14T18:48:27Z)
• Whose Opinions Do Language Models Reflect? [88.35520051971538]
  We investigate the opinions reflected by language models (LMs) by leveraging high-quality public opinion polls and their associated human responses. We find substantial misalignment between the views reflected by current LMs and those of US demographic groups. Our analysis confirms prior observations about the left-leaning tendencies of some human feedback-tuned LMs.
  arXiv  Detail & Related papers  (2023-03-30T17:17:08Z)

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.