Think-to-Talk or Talk-to-Think? When LLMs Come Up with an Answer in Multi-Hop Arithmetic Reasoning

• URL: http://arxiv.org/abs/2412.01113v3
• Date: Mon, 08 Sep 2025 17:43:53 GMT
• Title: Think-to-Talk or Talk-to-Think? When LLMs Come Up with an Answer in Multi-Hop Arithmetic Reasoning
• Authors: Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi, Shusaku Sone, Masaya Taniguchi, Ana Brassard, Keisuke Sakaguchi, Kentaro Inui,
• Abstract summary: We investigate when LMs internally resolve sub/whole problems through first reading the problem statements.<n>Our experiments reveal a systematic incremental reasoning strategy underlying LMs.<n> generated reasoning chains can be regarded as faithful reflections of the model's internal computation.
• Score: 29.193976295725637
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This study investigates the incremental, internal problem-solving process of language models (LMs) with arithmetic multi-hop reasoning as a case study. We specifically investigate when LMs internally resolve sub/whole problems through first reading the problem statements, generating reasoning chains, and achieving the final answer to mechanistically interpret LMs' multi-hop problem-solving process. Our experiments reveal a systematic incremental reasoning strategy underlying LMs. They have not derived an answer at the moment they first read the problem; instead, they obtain (sub)answers while generating the reasoning chain. Therefore, the generated reasoning chains can be regarded as faithful reflections of the model's internal computation.

Related papers

• Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn Interaction [57.67217258741752]
  Thinker is a hierarchical thinking model for deep search through multi-turn interaction.<n>It decomposes complex problems into independently solvable sub-problems.<n> dependencies between sub-problems are passed as parameters via these logical functions.
  arXiv  Detail & Related papers  (2025-11-11T07:48:45Z)
• Answer-Centric or Reasoning-Driven? Uncovering the Latent Memory Anchor in LLMs [28.556628696390767]
  Large Language Models (LLMs) demonstrate impressive reasoning capabilities.<n>Evidence suggests much of their success stems from memorized answer-reasoning patterns rather than genuine inference.<n>We propose a five-level answer-visibility prompt framework that systematically manipulates answer cues and probes model behavior through indirect, behavioral analysis.
  arXiv  Detail & Related papers  (2025-06-21T08:15:45Z)
• Computational Thinking Reasoning in Large Language Models [69.28428524878885]
  Computational Thinking Model (CTM) is a novel framework that incorporates computational thinking paradigms into large language models (LLMs)<n>Live code execution is seamlessly integrated into the reasoning process, allowing CTM to think by computing.<n>CTM outperforms conventional reasoning models and tool-augmented baselines in terms of accuracy, interpretability, and generalizability.
  arXiv  Detail & Related papers  (2025-06-03T09:11:15Z)
• Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models [76.6028674686018]
  We introduce thought-tracing, an inference-time reasoning algorithm to trace the mental states of agents. Our algorithm is modeled after the Bayesian theory-of-mind framework. We evaluate thought-tracing on diverse theory-of-mind benchmarks, demonstrating significant performance improvements.
  arXiv  Detail & Related papers  (2025-02-17T15:08:50Z)
• Critical-Questions-of-Thought: Steering LLM reasoning with Argumentative Querying [0.3659498819753633]
  State-of-the-art Large Language models (LLMs) continue to struggle when performing logical and mathematical reasoning. This paper makes use of the notion of critical questions from the literature on argumentation theory, focusing in particular on Toulmin's model of argumentation. We show that employing these critical questions can improve the reasoning capabilities of LLMs.
  arXiv  Detail & Related papers  (2024-12-19T18:51:30Z)
• FLARE: Faithful Logic-Aided Reasoning and Exploration [50.9814063216852]
  We introduce a novel approach for traversing the problem space using task decompositions. We use the Large Language Models to plan a solution, soft-formalise the query into facts and predicates using a logic programming code. Our method allows us to compute the faithfulness of the reasoning process w.r.t. the generated code and analyse the steps of the multi-hop search without relying on external solvers.
  arXiv  Detail & Related papers  (2024-10-14T19:39:11Z)
• Not All LLM Reasoners Are Created Equal [58.236453890457476]
  We study the depth of grade-school math problem-solving capabilities of LLMs. We evaluate their performance on pairs of existing math word problems together.
  arXiv  Detail & Related papers  (2024-10-02T17:01:10Z)
• STOC-TOT: Stochastic Tree-of-Thought with Constrained Decoding for Complex Reasoning in Multi-Hop Question Answering [8.525847131940031]
  Multi-hop question answering (MHQA) requires a model to retrieve and integrate information from multiple passages to answer a complex question. Recent systems leverage the power of large language models and integrate evidence retrieval with reasoning prompts. We propose STOC-TOT, a tree-of-thought reasoning prompting method with constrained decoding for MHQA.
  arXiv  Detail & Related papers  (2024-07-04T07:17:53Z)
• Distributional reasoning in LLMs: Parallel reasoning processes in multi-hop reasoning [8.609587510471943]
  We introduce a novel and interpretable analysis of internal multi-hop reasoning processes in large language models. We show that during inference, the middle layers of the network generate highly interpretable embeddings. Our findings can help uncover the strategies that LLMs use to solve reasoning tasks, offering insights into the types of thought processes that can emerge from artificial intelligence.
  arXiv  Detail & Related papers  (2024-06-19T21:36:40Z)
• How to think step-by-step: A mechanistic understanding of chain-of-thought reasoning [44.02173413922695]
  A lack of understanding prevails around the internal mechanisms of the models that facilitate Chain-of-Thought (CoT) prompting. This work investigates the sub-structures within Large Language Models that manifest CoT reasoning from a point of view.
  arXiv  Detail & Related papers  (2024-02-28T13:14:20Z)
• Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models [43.09706839884221]
  Boosting of Thoughts (BoT) is an automated prompting framework for problem solving with Large Language Models. We show that BoT consistently achieves higher or comparable problem-solving rates than other advanced prompting approaches.
  arXiv  Detail & Related papers  (2024-02-17T00:13:36Z)
• Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners? [140.9751389452011]
  We study the biases of large language models (LLMs) in relation to those known in children when solving arithmetic word problems. We generate a novel set of word problems for each of these tests, using a neuro-symbolic approach that enables fine-grained control over the problem features.
  arXiv  Detail & Related papers  (2024-01-31T18:48:20Z)
• Language Models can be Logical Solvers [99.40649402395725]
  We introduce LoGiPT, a novel language model that directly emulates the reasoning processes of logical solvers. LoGiPT is fine-tuned on a newly constructed instruction-tuning dataset derived from revealing and refining the invisible reasoning process of deductive solvers.
  arXiv  Detail & Related papers  (2023-11-10T16:23:50Z)
• Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models [107.07851578154242]
  Language models (LMs) have strong multi-step (i.e., procedural) reasoning capabilities. It is unclear whether LMs perform tasks by cheating with answers memorized from pretraining corpus, or, via a multi-step reasoning mechanism. We show that MechanisticProbe is able to detect the information of the reasoning tree from the model's attentions for most examples.
  arXiv  Detail & Related papers  (2023-10-23T01:47:29Z)
• Measuring Faithfulness in Chain-of-Thought Reasoning [19.074147845029355]
  Large language models (LLMs) perform better when they produce step-by-step, "Chain-of-Thought" (CoT) reasoning before answering a question. It is unclear if the stated reasoning is a faithful explanation of the model's actual reasoning (i.e., its process for answering the question) We investigate hypotheses for how CoT reasoning may be unfaithful, by examining how the model predictions change when we intervene on the CoT.
  arXiv  Detail & Related papers  (2023-07-17T01:08:39Z)
• Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic [84.59255070520673]
  Large language models (LLMs) face a challenge when engaging in temporal reasoning. We propose TempLogic, a novel framework designed specifically for temporal question-answering tasks.
  arXiv  Detail & Related papers  (2023-05-24T10:57:53Z)
• The Art of SOCRATIC QUESTIONING: Recursive Thinking with Large Language Models [45.01562498702836]
  Chain-of-Thought (CoT) prompting enables large language models to solve complex reasoning problems by generating intermediate steps. We propose SOCRATIC QUESTIONING, a divide-and-conquer style algorithm that mimics the recursive thinking process.
  arXiv  Detail & Related papers  (2023-05-24T10:36:14Z)
• HOP, UNION, GENERATE: Explainable Multi-hop Reasoning without Rationale Supervision [118.0818807474809]
  This work proposes a principled, probabilistic approach for training explainable multi-hop QA systems without rationale supervision. Our approach performs multi-hop reasoning by explicitly modeling rationales as sets, enabling the model to capture interactions between documents and sentences within a document.
  arXiv  Detail & Related papers  (2023-05-23T16:53:49Z)
• Faithful Question Answering with Monte-Carlo Planning [78.02429369951363]
  We propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps. We formulate the task as a discrete decision-making problem and solve it through the interaction of a reasoning environment and a controller. FAME achieves state-of-the-art performance on the standard benchmark.
  arXiv  Detail & Related papers  (2023-05-04T05:21:36Z)
• STREET: A Multi-Task Structured Reasoning and Explanation Benchmark [56.555662318619135]
  We introduce a unified multi-task and multi-domain natural language reasoning and explanation benchmark. We expect models to not only answer questions, but also produce step-by-step structured explanations describing how premises in the question are used to produce intermediate conclusions that can prove the correctness of a certain answer.
  arXiv  Detail & Related papers  (2023-02-13T22:34:02Z)
• Faithful Reasoning Using Large Language Models [12.132449274592668]
  We show how LMs can be made to perform faithful multi-step reasoning via a process whose causal structure mirrors the underlying logical structure of the problem. Our approach works by chaining together reasoning steps, where each step results from calls to two fine-tuned LMs. We demonstrate the effectiveness of our model on multi-step logical deduction and scientific question-answering, showing that it outperforms baselines on final answer accuracy.
  arXiv  Detail & Related papers  (2022-08-30T13:44:41Z)
• Discrete Reasoning Templates for Natural Language Understanding [79.07883990966077]
  We present an approach that reasons about complex questions by decomposing them to simpler subquestions. We derive the final answer according to instructions in a predefined reasoning template. We show that our approach is competitive with the state-of-the-art while being interpretable and requires little supervision.
  arXiv  Detail & Related papers  (2021-04-05T18:56:56Z)

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.