Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps

• URL: http://arxiv.org/abs/2503.19326v1
• Date: Tue, 25 Mar 2025 03:43:11 GMT
• Title: Process or Result? Manipulated Ending Tokens Can Mislead Reasoning LLMs to Ignore the Correct Reasoning Steps
• Authors: Yu Cui, Bryan Hooi, Yujun Cai, Yiwei Wang,
• Abstract summary: We explore how vulnerable are reasoning models to subtle errors in their input reasoning chains.<n>We introduce "Compromising Thought" (CPT), a vulnerability where models presented with reasoning tokens containing manipulated calculation results tend to ignore correct reasoning steps and adopt incorrect results instead.<n>Our work enhances understanding of reasoning robustness and highlights security considerations for reasoning-intensive applications.
• Score: 39.759594479826454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent reasoning large language models (LLMs) have demonstrated remarkable improvements in mathematical reasoning capabilities through long Chain-of-Thought. The reasoning tokens of these models enable self-correction within reasoning chains, enhancing robustness. This motivates our exploration: how vulnerable are reasoning LLMs to subtle errors in their input reasoning chains? We introduce "Compromising Thought" (CPT), a vulnerability where models presented with reasoning tokens containing manipulated calculation results tend to ignore correct reasoning steps and adopt incorrect results instead. Through systematic evaluation across multiple reasoning LLMs, we design three increasingly explicit prompting methods to measure CPT resistance, revealing that models struggle significantly to identify and correct these manipulations. Notably, contrary to existing research suggesting structural alterations affect model performance more than content modifications, we find that local ending token manipulations have greater impact on reasoning outcomes than structural changes. Moreover, we discover a security vulnerability in DeepSeek-R1 where tampered reasoning tokens can trigger complete reasoning cessation. Our work enhances understanding of reasoning robustness and highlights security considerations for reasoning-intensive applications.

Related papers

• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.190800043449336]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance. We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)
• Efficient Inference for Large Reasoning Models: A Survey [42.61170621552432]
  Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason. However, their deliberative reasoning process leads to inefficiencies in token usage, memory consumption, and inference time. This survey provides a review of efficient inference methods designed specifically for LRMs, focusing on mitigating token inefficiency while preserving the reasoning quality.
  arXiv  Detail & Related papers  (2025-03-29T13:27:46Z)
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models [54.04678363287392]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in complex tasks.<n>Recent advancements in OpenAI o1 and DeepSeek-R1 have further improved performance in System-2 reasoning domains.
  arXiv  Detail & Related papers  (2025-03-20T17:59:38Z)
• SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs [48.28847964704554]
  Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks. We propose a novel approach for continuous-space reasoning that does not require modifying the underlying LLM.
  arXiv  Detail & Related papers  (2025-02-17T18:52:29Z)
• Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability [53.51560766150442]
  Critical tokens are elements within reasoning trajectories that significantly influence incorrect outcomes.<n>We present a novel framework for identifying these tokens through rollout sampling.<n>We show that identifying and replacing critical tokens significantly improves model accuracy.
  arXiv  Detail & Related papers  (2024-11-29T18:58:22Z)
• Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning [52.83539473110143]
  We introduce a novel structure-oriented analysis method to help Large Language Models (LLMs) better understand a question. To further improve the reliability in complex question-answering tasks, we propose a multi-agent reasoning system, Structure-oriented Autonomous Reasoning Agents (SARA) Extensive experiments verify the effectiveness of the proposed reasoning system. Surprisingly, in some cases, the system even surpasses few-shot methods.
  arXiv  Detail & Related papers  (2024-10-18T05:30:33Z)
• Token-Supervised Value Models for Enhancing Mathematical Problem-Solving Capabilities of Large Language Models [56.32800938317095]
  Existing verifiers are sub-optimal for tree search techniques at test time.<n>We propose token-supervised value models (TVMs)<n>TVMs assign each token a probability that reflects the likelihood of reaching the correct final answer.
  arXiv  Detail & Related papers  (2024-07-12T13:16:50Z)
• Learning From Correctness Without Prompting Makes LLM Efficient Reasoner [30.203952806009717]
  Large language models (LLMs) have demonstrated outstanding performance across various tasks, yet they still exhibit limitations such as hallucination, unfaithful reasoning, and toxic content. We introduce an intrinsic self-correct reasoning framework for LLMs that eliminates the need for human feedback, external tools, and handcraft prompts.
  arXiv  Detail & Related papers  (2024-03-28T02:12:49Z)
• A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
  We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning. Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
  arXiv  Detail & Related papers  (2023-11-14T07:13:10Z)
• Are LLMs Rigorous Logical Reasoner? Empowering Natural Language Proof Generation with Contrastive Stepwise Decoding [10.421832675327712]
  We introduce contrastive decoding to stepwise proof generation, making use of negative reasoning paths to strengthen the model's capacity for logical deduction.<n> Experiments on EntailmentBank underscore the success of our method in augmenting the proof planning abilities of language models.
  arXiv  Detail & Related papers  (2023-11-12T05:12:49Z)
• Question Decomposition Improves the Faithfulness of Model-Generated Reasoning [23.34325378824462]
  Large language models (LLMs) are difficult to verify the correctness and safety of their behavior. One approach is to prompt LLMs to externalize their reasoning, by having them generate step-by-step reasoning as they answer a question. This approach relies on the stated reasoning faithfully reflecting the model's actual reasoning, which is not always the case. Decomposition-based methods achieve strong performance on question-answering tasks, sometimes approaching that of CoT.
  arXiv  Detail & Related papers  (2023-07-17T00:54:10Z)

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.