MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models

• URL: http://arxiv.org/abs/2603.28590v2
• Date: Thu, 02 Apr 2026 02:22:56 GMT
• Title: MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Language Models
• Abstract summary: Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs.<n>We propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs.
• Score: 17.655317708526603
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the actual reasons (i.e., decision-critical factors) driving the model's behavior, leading to the reduced CoT monitorability problem. However, a comprehensive and fully open-source benchmark for thoroughly evaluating CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,514 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize \textit{when} CoTs can be used to monitor the factors driving LLM behavior; and (2) two stress-test settings to quantify \textit{the extent to which} CoT monitorability can be degraded. Extensive experiments across multiple popular LLMs with varying capabilities show that CoT monitorability is higher when the decision-critical factors shape the intermediate reasoning process without merely influencing the final answer. More capable LLMs tend to exhibit lower monitorability. And all evaluated LLMs can intentionally reduce monitorability under stress-tests, with monitorability dropping by up to 30\% in some tasks that do not require structural reasoning over the decision-critical factors. Overall, MonitorBench provides a basis for further research on evaluating future LLMs, studying advanced stress-test monitorability techniques, and developing new monitoring approaches. The code is available at https://github.com/ASTRAL-Group/MonitorBench.

Related papers

• Does Out-of-Sight Equal Out-of-Mind in CoT Monitorability? [18.08925355421489]
  Chain-of-thought (CoT) reasoning offers a window into the decision-making of large language models.<n>Latent CoT approaches replace explicit tokens with a small number of continuous states, lowering inference costs but removing the readable trace this monitoring relies on.<n>We study this question with a hint-based intervention setup, a proxy for behaviors where models exploit biasing input cues.
  arXiv  Detail & Related papers  (2026-08-05T14:55:23Z)
• $D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing [63.49501120848927]
  Safety monitoring for large language models (D-LLMs) remains largely unexplored.<n>We propose $D2$-Monitor, a bi-level safety monitor for D-LLMs.<n>$D2$-Monitor adopts a lightweight probe as an always-on monitor to jointly estimate hesitation and perform base classification.
  arXiv  Detail & Related papers  (2026-05-25T14:22:21Z)
• Many-Shot CoT-ICL: Making In-Context Learning Truly Learn [58.439517684779936]
  In-context learning (ICL) adapts large language models to new tasks by conditioning on demonstrations in the prompt without parameter updates.<n>We study many-shot chain-of-thought in-context learning (CoT-ICL) for reasoning and show that standard many-shot rules do not transfer.
  arXiv  Detail & Related papers  (2026-05-13T13:30:12Z)
• Logic-Regularized Verifier Elicits Reasoning from LLMs [63.65875399266337]
  We propose LOVER, an unsupervised verifier regularized by logical rules.<n>Lover treats theverifier as a binary latent variable, utilizinginternal activations and enforcing three logical constraints.<n>Lover significantly outperforms unsupervised baselines.
  arXiv  Detail & Related papers  (2026-05-07T09:03:49Z)
• What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time [57.533031432715084]
  Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams.<n>Existing TTRL methods rely exclusively on positive pseudo-labeling strategies.<n>We propose SCRL, a robust test-time reinforcement learning framework that effectively mitigates label noise amplification.
  arXiv  Detail & Related papers  (2026-03-20T11:47:12Z)
• Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory [11.144603446849674]
  Chain-of-thought (CoT) monitors are systems that analyze reasoning traces to detect when outputs may exhibit attributes of interest.<n>In this paper, we show that non-zero mutual information between CoT and output is a necessary but not sufficient condition for CoT monitorability.
  arXiv  Detail & Related papers  (2026-02-20T15:50:30Z)
• No Global Plan in Chain-of-Thought: Uncover the Latent Planning Horizon of LLMs [65.783709850324]
  This work stems from prior complementary observations on the dynamics of Chain-of-Thought (CoT): Large Language Models (LLMs)<n>LLMs are shown latent planning of subsequent reasoning prior to CoT emergence, thereby diminishing the significance of explicit CoT.<n>We investigate the latent planning strength of LLMs, through our probing method, Tele-Lens, applying to hidden states across diverse task domains.
  arXiv  Detail & Related papers  (2026-02-02T13:46:56Z)
• AutoMonitor-Bench: Evaluating the Reliability of LLM-Based Misbehavior Monitor [19.39430341586964]
  AutoMonitor-Bench is the first benchmark to systematically evaluate the reliability of misbehavior monitors across diverse tasks and failure modes.<n>We evaluate monitors using two complementary metrics: Miss Rate (MR) and False Alarm Rate (FAR), capturing failures to detect misbehavior and oversensitivity to benign behavior, respectively.<n>We construct a large-scale training corpus of 153,581 samples and fine-tune Qwen3-4B-Instruction to investigate whether training on known, relatively easy-to-construct misbehavior datasets improves monitoring performance on unseen and more implicit misbehaviors.
  arXiv  Detail & Related papers  (2026-01-09T12:09:45Z)
• Monitoring Monitorability [7.993120960324396]
  We propose three evaluation archetypes (intervention, process, and outcome-property) and a new monitorability metric.<n>We compare the monitorability of various frontier models and find that most models are fairly, but not perfectly, monitorable.<n>We show we can improve monitorability by asking models follow-up questions and giving their follow-up CoT to the monitor.
  arXiv  Detail & Related papers  (2025-12-20T10:46:04Z)
• Investigating CoT Monitorability in Large Reasoning Models [10.511177985572333]
  Large Reasoning Models (LRMs) have demonstrated remarkable performance on complex tasks by engaging in extended reasoning before producing final answers.<n>These detailed reasoning traces also create a new opportunity for AI safety, CoT Monitorability.<n>However, two key fundamental challenges arise when attempting to build more effective monitors through CoT analysis.
  arXiv  Detail & Related papers  (2025-11-11T18:06:34Z)
• CoT-Saliency: Unified Chain-of-Thought Reasoning for Heterogeneous Saliency Tasks [96.64597365827046]
  We present the first unified framework that jointly handles three operationally heterogeneous saliency tasks.<n>We introduce a Chain-of-Thought (CoT) reasoning process in a Vision-Language Model (VLM) to bridge task heterogeneity.<n>We show our model matches or outperforms specialized SOTA methods and strong closed-source VLMs across all tasks.
  arXiv  Detail & Related papers  (2025-11-01T04:37:01Z)
• FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning [62.452350134196934]
  FaithCoT-Bench is a unified benchmark for instance-level CoT unfaithfulness detection.<n>Our framework formulates unfaithfulness detection as a discriminative decision problem.<n>FaithCoT-Bench sets a solid basis for future research toward more interpretable and trustworthy reasoning in LLMs.
  arXiv  Detail & Related papers  (2025-10-05T05:16:54Z)
• Beyond Linear Probes: Dynamic Safety Monitoring for Language Models [67.15793594651609]
  Traditional safety monitors require the same amount of compute for every query.<n>We introduce Truncated Polynomials (TPCs), a natural extension of linear probes for dynamic activation monitoring.<n>Our key insight is that TPCs can be trained and evaluated progressively, term-by-term.
  arXiv  Detail & Related papers  (2025-09-30T13:32:59Z)
• Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation [56.102976602468615]
  We show that we can monitor a frontier reasoning model, such as OpenAI o3-mini, for reward hacking in agentic coding environments.<n>We find that with too much optimization, agents learn obfuscated reward hacking, hiding their intent within the chain-of-thought.
  arXiv  Detail & Related papers  (2025-03-14T23:50:34Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)

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.