DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMs

• URL: http://arxiv.org/abs/2503.15793v4
• Date: Fri, 18 Apr 2025 02:38:12 GMT
• Title: DNR Bench: Benchmarking Over-Reasoning in Reasoning LLMs
• Authors: Masoud Hashemi, Oluwanifemi Bamgbose, Sathwik Tejaswi Madhusudhan, Jishnu Sethumadhavan Nair, Aman Tiwari, Vikas Yadav,
• Abstract summary: We introduce Don't Reason Bench (DNR Bench) to evaluate large language models (LLMs)<n>DNR Bench consists of 150 adversarially designed prompts that are easy for humans to understand and respond to.<n>Our experiments reveal that RLMs generate up to 70x more tokens than necessary, often failing at tasks that simpler non-reasoning models handle efficiently with higher accuracy.
• Score: 3.850766603072179
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Test-time scaling has significantly improved large language model performance, enabling deeper reasoning to solve complex problems. However, this increased reasoning capability also leads to excessive token generation and unnecessary problem-solving attempts. We introduce Don\'t Reason Bench (DNR Bench), a new benchmark designed to evaluate LLMs ability to robustly understand the tricky reasoning triggers and avoiding unnecessary generation. DNR Bench consists of 150 adversarially designed prompts that are easy for humans to understand and respond to, but surprisingly not for many of the recent prominent LLMs. DNR Bench tests models abilities across different capabilities, such as instruction adherence, hallucination avoidance, redundancy filtering, and unanswerable question recognition. We evaluate reasoning LLMs (RLMs), including DeepSeek-R1, OpenAI O3-mini, Claude-3.7-sonnet and compare them against a powerful non-reasoning model, e.g., GPT-4o. Our experiments reveal that RLMs generate up to 70x more tokens than necessary, often failing at tasks that simpler non-reasoning models handle efficiently with higher accuracy. Our findings underscore the need for more effective training and inference strategies in RLMs.

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)
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning [87.30285670315334]
  textbfR1-Searcher is a novel two-stage outcome-based RL approach designed to enhance the search capabilities of Large Language Models. Our framework relies exclusively on RL, without requiring process rewards or distillation for a cold start. Our experiments demonstrate that our method significantly outperforms previous strong RAG methods, even when compared to the closed-source GPT-4o-mini.
  arXiv  Detail & Related papers  (2025-03-07T17:14:44Z)
• R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model [70.77691645678804]
  We present the first successful replication of emergent characteristics for multimodal reasoning on only a non-SFT 2B model. Our model achieves 59.47% accuracy on CVBench, outperforming the base model by approximately 30% and exceeding both SFT setting by 2%. In addition, we share our failed attempts and insights in attempting to achieve R1-like reasoning using RL with instruct models.
  arXiv  Detail & Related papers  (2025-03-07T04:21:47Z)
• LR$^2$Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems [7.379503137362718]
  We introduce LR$2$Bench, a novel benchmark designed to evaluate the Long-chain Reflective Reasoning capabilities of Large Language Models (LLMs)<n>Our experimental results reveal that even the most advanced reasoning-specific models, such as DeepSeek-R1 and OpenAI o1-preview, struggle with tasks in LR$2$Bench.
  arXiv  Detail & Related papers  (2025-02-25T04:51:17Z)
• CounterBench: A Benchmark for Counterfactuals Reasoning in Large Language Models [5.409370027524351]
  We evaluate the performance of large language models (LLMs) in counterfactual reasoning.<n>We introduce a new benchmark dataset, CounterBench, comprising 1K counterfactual reasoning questions.
  arXiv  Detail & Related papers  (2025-02-16T06:19:37Z)
• On the Emergence of Thinking in LLMs I: Searching for the Right Intuition [34.32871896067864]
  We propose a post-training framework called Reinforcement Learning via Self-Play (RLSP)<n> RLSP involves three steps: supervised fine-tuning with human or synthetic demonstrations of the reasoning process, using an exploration reward signal to encourage diverse and efficient reasoning behaviors, and RL training with an outcome verifier to ensure correctness while preventing reward hacking.<n> Empirical studies in the math domain show that RLSP improves reasoning.
  arXiv  Detail & Related papers  (2025-02-10T18:52:04Z)
• Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding [74.31981011985681]
  Large language models (LLMs) have shown impressive capabilities, but still struggle with complex reasoning tasks requiring multiple steps. We introduce LaTent Reasoning Optimization (LaTRO), a principled framework that formulates reasoning as sampling from a latent distribution. We validate LaTRO through experiments on GSM8K and ARC-Challenge datasets using multiple model architectures.
  arXiv  Detail & Related papers  (2024-11-06T22:02:30Z)
• WILT: A Multi-Turn, Memorization-Robust Inductive Logic Benchmark for LLMs [0.8883751685905831]
  We introduce the Wason Inductive Logic Test (WILT), a simple yet challenging multi-turn reasoning benchmark designed to resist memorization. Our findings reveal that LLMs struggle with this task, exhibiting distinct strengths and weaknesses. Despite these variations, the best-performing model achieves only 28% accuracy, highlighting a significant gap in LLM performance on complex multi-turn reasoning tasks.
  arXiv  Detail & Related papers  (2024-10-14T18:29:13Z)
• 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)
• SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning [55.76083560152823]
  SelfCheck is a general-purpose zero-shot verification schema for recognizing errors in step-by-step reasoning. We test SelfCheck on three datasets (GSM8K, MathQA, and MATH) and find that it successfully recognizes errors and, in turn, increases final answer accuracies.
  arXiv  Detail & Related papers  (2023-08-01T10:31:36Z)
• Rethinking with Retrieval: Faithful Large Language Model Inference [91.66406351103484]
  We propose a novel post-processing approach, rethinking with retrieval (RR) RR retrieves relevant external knowledge based on the reasoning steps obtained from the chain-of-thought prompting. We evaluate the effectiveness of RR through extensive experiments with GPT-3 on three complex reasoning tasks.
  arXiv  Detail & Related papers  (2022-12-31T22:35:34Z)

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.