From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models

• URL: http://arxiv.org/abs/2509.23676v1
• Date: Sun, 28 Sep 2025 06:32:21 GMT
• Title: From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models
• Authors: Jue Zhang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang,
• Abstract summary: We conduct a three-stage investigation into the interplay between reasoning and answer generation in three distilled DeepSeek R1 models.<n>We demonstrate that including explicit reasoning consistently improves answer quality across diverse domains.<n>Our results show that perturbations to key reasoning tokens can reliably alter the final answers.
• Score: 48.01707022738742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Reasoning Models (LRMs) generate explicit reasoning traces alongside final answers, yet the extent to which these traces influence answer generation remains unclear. In this work, we conduct a three-stage investigation into the interplay between reasoning and answer generation in three distilled DeepSeek R1 models. First, through empirical evaluation, we demonstrate that including explicit reasoning consistently improves answer quality across diverse domains. Second, attention analysis reveals that answer tokens attend substantially to reasoning tokens, with certain mid-layer Reasoning-Focus Heads (RFHs) closely tracking the reasoning trajectory, including self-reflective cues. Third, we apply mechanistic interventions using activation patching to assess the dependence of answer tokens on reasoning activations. Our results show that perturbations to key reasoning tokens can reliably alter the final answers, confirming a directional and functional flow of information from reasoning to answer. These findings deepen our understanding of how LRMs leverage reasoning tokens for answer generation, highlighting the functional role of intermediate reasoning in shaping model outputs. Our data and code are publicly available at \href{https://aka.ms/R2A-code}{this URL}.

Related papers

• Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution [79.98699884805636]
  Reasoning Execution by Multiple Listeners (REMUL) is a multi-party reinforcement learning approach.<n>REMUL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful.<n>Speakers are rewarded for producing reasoning that is clear to listeners.
  arXiv  Detail & Related papers  (2026-02-18T02:55:55Z)
• Thinking Forward and Backward: Multi-Objective Reinforcement Learning for Retrieval-Augmented Reasoning [137.33138614095435]
  Retrieval-augmented generation (RAG) has proven to be effective in mitigating hallucinations in large language models.<n>Recent efforts have incorporated search-based interactions into RAG, enabling iterative reasoning with real-time retrieval.<n>We propose Bi-RAR, a novel retrieval-augmented reasoning framework that evaluates each intermediate step jointly in both forward and backward directions.
  arXiv  Detail & Related papers  (2025-11-12T08:29:39Z)
• Internal states before wait modulate reasoning patterns [14.272989515787351]
  We train crosscoders at multiple layers of DeepSeek-R1-Distill-Llama-8B and introduce a latent attribution technique in the crosscoder setting.<n>We locate a small set of features relevant for promoting/suppressing wait tokens' probabilities.<n>We show that many of our identified features indeed are relevant for the reasoning process.
  arXiv  Detail & Related papers  (2025-10-05T10:03:42Z)
• Reasoning or Retrieval? A Study of Answer Attribution on Large Reasoning Models [15.797612515648412]
  Large reasoning models (LRMs) exhibit unprecedented capabilities in solving complex problems through Chain-of-Thought (CoT) reasoning.<n>Recent studies reveal that their final answers often contradict their own reasoning traces.<n>We hypothesize that this inconsistency stems from two competing mechanisms for generating answers: CoT reasoning and memory retrieval.<n>We introduce FARL, a novel fine-tuning framework that integrates memory unlearning with reinforcement learning.
  arXiv  Detail & Related papers  (2025-09-29T01:13:33Z)
• 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)
• On Reasoning Strength Planning in Large Reasoning Models [50.61816666920207]
  We find evidence that LRMs pre-plan the reasoning strengths in their activations even before generation.<n>We then uncover that LRMs encode this reasoning strength through a pre-allocated directional vector embedded in the activations of the model.<n>Our work provides new insights into the internal mechanisms of reasoning in LRMs and offers practical tools for controlling their reasoning behaviors.
  arXiv  Detail & Related papers  (2025-06-10T02:55:13Z)
• Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning [33.040747962183076]
  Large reasoning models (LRMs) have demonstrated impressive capabilities in complex problem-solving, yet their internal reasoning mechanisms remain poorly understood.<n>We observe an interesting MI peaks phenomenon: the MI at specific generative steps exhibits a sudden and significant increase during LRM's reasoning process.<n>We then demonstrate that these thinking tokens are crucial for LRM's reasoning performance, while other tokens has minimal impacts.
  arXiv  Detail & Related papers  (2025-06-03T13:31:10Z)
• Self-Critique Guided Iterative Reasoning for Multi-hop Question Answering [24.446222685949227]
  Large language models (LLMs) face challenges in knowledge-intensive multi-hop reasoning.<n>We propose Self-Critique Guided Iterative Reasoning (SiGIR)<n>SiGIR uses self-critique feedback to guide the iterative reasoning process.
  arXiv  Detail & Related papers  (2025-05-25T12:10:24Z)
• Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment [54.62926010621013]
  We introduce a novel task, code reasoning, to provide a new perspective for the reasoning abilities of large language models.<n>We summarize three meta-benchmarks based on established forms of logical reasoning, and instantiate these into eight specific benchmark tasks.<n>We present a new pathway exploration pipeline inspired by human intricate problem-solving methods.
  arXiv  Detail & Related papers  (2025-02-17T10:39:58Z)
• Preemptive Answer "Attacks" on Chain-of-Thought Reasoning [7.233752893356647]
  Large language models (LLMs) showcase impressive reasoning capabilities when coupled with Chain-of-Thought prompting. In this paper, we introduce a novel scenario termed preemptive answers, where the LLM obtains an answer before engaging in reasoning. Experiments reveal that preemptive answers significantly impair the model's reasoning capability across various CoT methods and a broad spectrum of datasets.
  arXiv  Detail & Related papers  (2024-05-31T15:15:04Z)

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.