Latent Debate: A Surrogate Framework for Interpreting LLM Thinking

• URL: http://arxiv.org/abs/2512.01909v1
• Date: Mon, 01 Dec 2025 17:27:31 GMT
• Title: Latent Debate: A Surrogate Framework for Interpreting LLM Thinking
• Authors: Lihu Chen, Xiang Yin, Francesca Toni,
• Abstract summary: We introduce latent debate, a novel framework for interpreting model predictions through the lens of implicit internal arguments.<n>We show that latent debate is a faithful structured surrogate model that has highly consistent predictions with the original LLM.<n>Further analysis reveals strong correlations between hallucinations and debate patterns, such as a high degree of latent debates in the middle layers is linked to a higher risk of hallucinations.
• Score: 26.20998021856433
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding the internal thinking process of Large Language Models (LLMs) and the cause of hallucinations remains a key challenge. To this end, we introduce latent debate, a novel framework for interpreting model predictions through the lens of implicit internal arguments. Unlike the current work of self-consistency and multi-agent debate, which relies on explicit debates among multiple answers or multiple models, latent debate captures the hidden supporting and attacking signals that arise within a single model during a single inference. We first present a model- and task-agnostic conceptual framework, and then instantiate it symbolically to approximate the thinking process of LLMs on True/False prediction tasks. Empirical studies demonstrate that latent debate is a faithful structured surrogate model that has highly consistent predictions with the original LLM. Beyond interpretability, we demonstrate that latent debate provides a strong baseline for hallucination detection. Further analysis reveals strong correlations between hallucinations and debate patterns, such as a high degree of latent debates in the middle layers is linked to a higher risk of hallucinations. These findings position latent debate as a potential framework for understanding internal mechanisms of LLMs, especially for scenarios where internal (dis)agreements appear during the inference steps.

Related papers

• Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models [77.98801218316505]
  Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning.<n>We investigate the internal processing of LLMs during in-context concept inference.
  arXiv  Detail & Related papers  (2026-02-08T03:14:39Z)
• Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts [74.47786985522762]
  We identify a critical failure mode termed textual inertia, where models tend to blindly adhere to the erroneous text while neglecting conflicting visual evidence.<n>We propose the LogicGraph Perturbation Protocol that structurally injects perturbations into the reasoning chains of diverse LMMs.<n>Results reveal that models successfully self-correct in less than 10% of cases and predominantly succumb to blind textual error propagation.
  arXiv  Detail & Related papers  (2026-01-07T16:39:34Z)
• Robust Multimodal Large Language Models Against Modality Conflict [94.12341487880465]
  multimodal large language models (MLLMs) are prone to hallucinations in real-world scenarios.<n>We study the inherent conflicts in inputs from different modalities that place MLLMs in a dilemma and directly lead to hallucinations.<n>Three methods are proposed to alleviate the hallucination caused by modality conflict.
  arXiv  Detail & Related papers  (2025-07-09T11:18:38Z)
• A Survey on Latent Reasoning [100.54120559169735]
  Large Language Models (LLMs) have demonstrated impressive reasoning capabilities.<n>CoT reasoning that verbalizes intermediate steps limits the model's expressive bandwidth.<n>Latent reasoning tackles this bottleneck by performing multi-step inference entirely in the model's continuous hidden state.
  arXiv  Detail & Related papers  (2025-07-08T17:29:07Z)
• Debating for Better Reasoning: An Unsupervised Multimodal Approach [56.74157117060815]
  We extend the debate paradigm to a multimodal setting, exploring its potential for weaker models to supervise and enhance the performance of stronger models.<n>We focus on visual question answering (VQA), where two "sighted" expert vision-language models debate an answer, while a "blind" (text-only) judge adjudicates based solely on the quality of the arguments.<n>In our framework, the experts defend only answers aligned with their beliefs, thereby obviating the need for explicit role-playing and concentrating the debate on instances of expert disagreement.
  arXiv  Detail & Related papers  (2025-05-20T17:18:17Z)
• Large Language Models Understanding: an Inherent Ambiguity Barrier [0.0]
  A lively ongoing debate is taking place, since the emergence of Large Language Models (LLMs) with regards to their capability to understand the world.<n>Arguments and counter-arguments have been proposed based upon thought experiments, anecdotal conversations between LLMs and humans, statistical linguistic analysis, philosophical considerations, and more.<n>In this brief paper we present a counter-argument based upon a thought experiment and semi-formal considerations leading to an inherent ambiguity barrier.
  arXiv  Detail & Related papers  (2025-05-01T16:55:44Z)
• The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning [56.574829311863446]
  Chain-of-Thought (CoT) prompting has been widely recognized for its ability to enhance reasoning capabilities in large language models (LLMs)<n>We demonstrate that CoT and its reasoning variants consistently underperform direct answering across varying model scales and benchmark complexities.<n>Our analysis uncovers a fundamental hybrid mechanism of explicit-implicit reasoning driving CoT's performance in pattern-based ICL.
  arXiv  Detail & Related papers  (2025-04-07T13:51:06Z)
• Calibrating Reasoning in Language Models with Internal Consistency [18.24350001344488]
  Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks.<n>LLMs often generate text with obvious mistakes and contradictions.<n>In this work, we investigate reasoning in LLMs through the lens of internal representations.
  arXiv  Detail & Related papers  (2024-05-29T02:44:12Z)
• What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models [50.97705264224828]
  We propose Counterfactual Inception, a novel method that implants counterfactual thinking into Large Multi-modal Models. We aim for the models to engage with and generate responses that span a wider contextual scene understanding. Comprehensive analyses across various LMMs, including both open-source and proprietary models, corroborate that counterfactual thinking significantly reduces hallucination.
  arXiv  Detail & Related papers  (2024-03-20T11:27:20Z)

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.