DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning

• URL: http://arxiv.org/abs/2504.07128v2
• Date: Mon, 12 May 2025 18:14:34 GMT
• Title: DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
• Authors: Sara Vera Marjanović, Arkil Patel, Vaibhav Adlakha, Milad Aghajohari, Parishad BehnamGhader, Mehar Bhatia, Aditi Khandelwal, Austin Kraft, Benno Krojer, Xing Han Lù, Nicholas Meade, Dongchan Shin, Amirhossein Kazemnejad, Gaurav Kamath, Marius Mosbach, Karolina Stańczak, Siva Reddy,
• Abstract summary: We investigate the impact and controllability of DeepSeek-R1's thought length, management of long or confusing contexts, cultural and safety concerns.<n>We show DeepSeek-R1 has a'sweet spot' of reasoning, where extra inference time can impair model performance.<n>We also note strong safety vulnerabilities of DeepSeek-R1 compared to its non-reasoning counterpart.
• Score: 31.805726635329595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an answer for a given input, DeepSeek-R1 creates detailed multi-step reasoning chains, seemingly "thinking" about a problem before providing an answer. This reasoning process is publicly available to the user, creating endless opportunities for studying the reasoning behaviour of the model and opening up the field of Thoughtology. Starting from a taxonomy of DeepSeek-R1's basic building blocks of reasoning, our analyses on DeepSeek-R1 investigate the impact and controllability of thought length, management of long or confusing contexts, cultural and safety concerns, and the status of DeepSeek-R1 vis-\`a-vis cognitive phenomena, such as human-like language processing and world modelling. Our findings paint a nuanced picture. Notably, we show DeepSeek-R1 has a 'sweet spot' of reasoning, where extra inference time can impair model performance. Furthermore, we find a tendency for DeepSeek-R1 to persistently ruminate on previously explored problem formulations, obstructing further exploration. We also note strong safety vulnerabilities of DeepSeek-R1 compared to its non-reasoning counterpart, which can also compromise safety-aligned LLMs.

Related papers

• Are Large Language Models Capable of Deep Relational Reasoning? Insights from DeepSeek-R1 and Benchmark Comparisons [11.429641860623143]
  We evaluate and compare the reasoning capabilities of three cutting-edge Large Language Models (LLMs)<n>DeepSeek-R1 consistently achieves the highest F1-scores across multiple tasks and problem sizes.<n>A detailed analysis of DeepSeek-R1's long Chain-of-Thought responses uncovers its unique planning and verification strategies.
  arXiv  Detail & Related papers  (2025-06-29T07:37:49Z)
• Lost at the Beginning of Reasoning [82.18834329384514]
  We show that the first reasoning step exerts a disproportionately large influence on the final prediction.<n>We propose an efficient sampling strategy that leverages a reward model to identify and retain high-quality first reasoning steps.<n>We introduce a new benchmark specifically constructed with deliberately flawed first reasoning steps to systematically evaluate model self-correction capabilities.
  arXiv  Detail & Related papers  (2025-06-27T09:53:57Z)
• Excessive Reasoning Attack on Reasoning LLMs [26.52688123765127]
  In this work, we expose a novel threat: adversarial inputs can be crafted to exploit excessive reasoning behaviors.<n>Our results demonstrate a 3x to 9x increase in reasoning length with comparable utility performance.<n>Our crafted adversarial inputs exhibit transferability, inducing computational overhead in o3-mini, o1-mini, DeepSeek-R1, and QWQ models.
  arXiv  Detail & Related papers  (2025-06-17T10:16:52Z)
• OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation [33.008513399946914]
  OThink-R1 is a method that prunes redundant reasoning steps while preserving logical validity.<n> Experiments across mathematical and question-answering tasks demonstrate that OThink-R1 reduces reasoning redundancy by almost 23% on average.
  arXiv  Detail & Related papers  (2025-06-03T03:31:30Z)
• Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning [96.01617809845396]
  Ground-R1 is a reinforcement learning framework that enables grounded visual reasoning without requiring explicit evidence or rationale annotations.<n>Ground-R1 achieves superior performance and exhibits emergent cognitive behaviors such as uncertainty awareness, spatial perception, and iterative refinement.
  arXiv  Detail & Related papers  (2025-05-26T17:51:47Z)
• RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability [29.437113221903715]
  We introduce RealSafe-R1 as safety-aligned versions of DeepSeek-R1 models. Our method preserves the models' reasoning capabilities by maintaining the training data within the original distribution of generation.
  arXiv  Detail & Related papers  (2025-04-14T10:26:37Z)
• Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities [101.77467538102924]
  Recent advancements in Large Reasoning Models (LRMs) have demonstrated remarkable performance in specialized reasoning tasks. We show that acquiring deliberative reasoning capabilities significantly reduces the foundational capabilities of LRMs. We demonstrate that adaptive reasoning -- employing modes like Zero-Thinking, Less-Thinking, and Summary-Thinking -- can effectively alleviate these drawbacks.
  arXiv  Detail & Related papers  (2025-03-23T08:18:51Z)
• The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1 [70.94607997570729]
  We present a comprehensive safety assessment of OpenAI-o3 and DeepSeek-R1 reasoning models.<n>We investigate their susceptibility to adversarial attacks, such as jailbreaking and prompt injection, to assess their robustness in real-world applications.
  arXiv  Detail & Related papers  (2025-02-18T09:06:07Z)
• 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)
• Semantic Specialization in MoE Appears with Scale: A Study of DeepSeek R1 Expert Specialization [7.457737671087695]
  DeepSeek-R1, the largest open-source Mixture-of-Experts (MoE) model, has demonstrated reasoning capabilities comparable to proprietary frontier models.<n>We investigate whether its routing mechanism exhibits greater semantic specialization than previous MoE models.<n>We conclude that DeepSeek-R1's routing mechanism is more semantically aware and it engages in structured cognitive processes.
  arXiv  Detail & Related papers  (2025-02-15T23:37:32Z)
• Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs [86.79757571440082]
  Large language models (LLMs) such as OpenAI's o1 have demonstrated remarkable abilities in complex reasoning tasks.<n>We identify a phenomenon we term underthinking, where o1-like LLMs frequently switch between different reasoning thoughts.<n>We propose a decoding strategy with thought switching penalty TIP that discourages premature transitions between thoughts.
  arXiv  Detail & Related papers  (2025-01-30T18:58:18Z)
• Challenges in Ensuring AI Safety in DeepSeek-R1 Models: The Shortcomings of Reinforcement Learning Strategies [0.0]
  This paper examines the limitations of Reinforcement Learning as the primary approach for reducing harmful outputs in DeepSeek-R1.<n>We propose hybrid training approaches combining RL and Supervised Fine-Tuning to achieve robust harmlessness reduction.
  arXiv  Detail & Related papers  (2025-01-28T15:52:51Z)
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning [147.16121855209246]
  We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.<n>DeepSeek-R1-Zero is trained via large-scale reinforcement learning.<n>DeepSeek-R1 incorporates multi-stage training and cold-start data before RL.
  arXiv  Detail & Related papers  (2025-01-22T15:19:35Z)

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.