THiNK: Can Large Language Models Think-aloud?

• URL: http://arxiv.org/abs/2505.20184v1
• Date: Mon, 26 May 2025 16:27:02 GMT
• Title: THiNK: Can Large Language Models Think-aloud?
• Abstract summary: We propose THiNK, a multi-agent, feedback-driven evaluation framework grounded in Bloom's taxonomy.<n>We apply THiNK to seven state-of-the-art language models and perform a cognitive analysis of their outputs.<n>Results reveal that models reliably perform lower-order categories well, but struggle with applying knowledge in realistic contexts.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Assessing higher-order thinking skills in large language models (LLMs) remains a fundamental challenge, especially in tasks that go beyond surface-level accuracy. In this work, we propose THiNK (Testing Higher-order Notion of Knowledge), a multi-agent, feedback-driven evaluation framework grounded in Bloom's Taxonomy. THiNK frames reasoning assessment as an iterative task of problem generation, critique, and revision, encouraging LLMs to think-aloud through step-by-step reflection and refinement. This enables a systematic evaluation of both lower-order (e.g., remember, understand) and higher-order (e.g., evaluate, create) thinking skills. We apply THiNK to seven state-of-the-art LLMs and perform a detailed cognitive analysis of their outputs. Results reveal that while models reliably perform lower-order categories well, they struggle with applying knowledge in realistic contexts and exhibit limited abstraction. Structured feedback loops significantly improve reasoning performance, particularly in higher-order thinking. Qualitative evaluations further confirm that THiNK-guided outputs better align with domain logic and problem structure. The code of our framework provides a scalable methodology for probing and enhancing LLM reasoning, offering new directions for evaluation grounded in learning science, which is available at our GitHub repository.

Related papers

• RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models [54.53236295237077]
  We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning.<n> Output Prediction measures fine-grained, stateful execution reasoning across files.<n>Call Chain Prediction evaluates high-level architectural dependency understanding under noisy context.
  arXiv  Detail & Related papers  (2026-07-28T17:12:41Z)
• Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs [8.10827298136302]
  Large language models (LLMs) have recently advanced automatic design (AHD) for optimization (CO)<n>Most existing approaches search over executable programs and distill insights from execution feedback to guide later iterations.<n>We argue that knowledge becomes the primary search object and code merely instantiates and tests it.
  arXiv  Detail & Related papers  (2026-05-07T12:30:58Z)
• METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models [61.33372454250959]
  Contextual causal reasoning is a critical yet challenging capability for Large Language Models.<n>Existing benchmarks fail to ensure context consistency or cover the full causal hierarchy.<n>We pioneer METER to systematically benchmark LLMs across all three levels of the causal ladder.
  arXiv  Detail & Related papers  (2026-04-13T14:07:11Z)
• An Empirical Study of Reasoning Steps in Thinking Code LLMs [8.653365851909745]
  Thinking Large Language Models generate explicit intermediate reasoning traces before final answers.<n>This study examines the reasoning process and quality of thinking LLMs for code generation.
  arXiv  Detail & Related papers  (2025-11-08T06:18:48Z)
• Re-ranking Reasoning Context with Tree Search Makes Large Vision-Language Models Stronger [51.01841635655944]
  Recent advancements in Large Vision Language Models (LVLMs) have significantly improved performance in Visual Question Answering (VQA) tasks.<n>Existing methods still face challenges, such as the scarcity of knowledge with reasoning examples and erratic responses from retrieved knowledge.<n>We propose a multimodal RAG framework, termed RCTS, which enhances LVLMs by constructing a Reasoning Context-enriched knowledge base and a Tree Search re-ranking method.
  arXiv  Detail & Related papers  (2025-06-09T14:00:57Z)
• Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study [34.29839553042609]
  We propose FineLogic, a fine-grained evaluation framework that assesses logical reasoning across three dimensions.<n>We conduct a study on the effects of supervision format during fine-tuning.<n>Our findings reveal that natural language supervision yields strong generalization even on out-of-distribution and long-context tasks.
  arXiv  Detail & Related papers  (2025-06-05T09:34:12Z)
• Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation [75.26829371493189]
  Large language models (LLMs) have demonstrated impressive reasoning capacities that mirror human-like thinking.<n>Existing reasoning benchmarks either focus on domain-specific knowledge (crystallized intelligence) or lack interpretability.<n>We propose DRE-Bench, a dynamic reasoning evaluation benchmark grounded in a hierarchical cognitive framework.
  arXiv  Detail & Related papers  (2025-06-03T09:01:08Z)
• RealCritic: Towards Effectiveness-Driven Evaluation of Language Model Critiques [59.861013614500024]
  We introduce a new benchmark designed to assess the critique capabilities of Large Language Models (LLMs)<n>Unlike existing benchmarks, which typically function in an open-loop fashion, our approach employs a closed-loop methodology that evaluates the quality of corrections generated from critiques.
  arXiv  Detail & Related papers  (2025-01-24T13:48:10Z)
• Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks [68.49251303172674]
  State-of-the-art large language models (LLMs) exhibit impressive problem-solving capabilities but may struggle with complex reasoning and factual correctness. Existing methods harness the strengths of chain-of-thought and retrieval-augmented generation (RAG) to decompose a complex problem into simpler steps and apply retrieval to improve factual correctness. We introduce Critic-guided planning with Retrieval-augmentation, CR-Planner, a novel framework that leverages fine-tuned critic models to guide both reasoning and retrieval processes through planning.
  arXiv  Detail & Related papers  (2024-10-02T11:26:02Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Can Github issues be solved with Tree Of Thoughts? [0.0]
  This research introduces the application of the Tree of Thoughts (ToT) language model reasoning framework for enhancing the decision-making and problem-solving abilities of LLMs. We experimentally deploy ToT in tackling a Github issue contained within an instance of the SWE-bench.
  arXiv  Detail & Related papers  (2024-05-20T11:05:56Z)
• HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation [20.178644251662316]
  We introduce the hierarchical graph of thoughts (HGOT) to enhance the retrieval of pertinent passages during in-context learning. The framework employs the divide-and-conquer strategy to break down complex queries into manageable sub-queries. It refines self-consistency majority voting for answer selection, which incorporates the recently proposed citation recall and precision metrics.
  arXiv  Detail & Related papers  (2024-02-14T18:41:19Z)
• CLOMO: Counterfactual Logical Modification with Large Language Models [109.60793869938534]
  We introduce a novel task, Counterfactual Logical Modification (CLOMO), and a high-quality human-annotated benchmark. In this task, LLMs must adeptly alter a given argumentative text to uphold a predetermined logical relationship. We propose an innovative evaluation metric, the Self-Evaluation Score (SES), to directly evaluate the natural language output of LLMs.
  arXiv  Detail & Related papers  (2023-11-29T08:29:54Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)

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.