THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models

• URL: http://arxiv.org/abs/2504.13367v1
• Date: Thu, 17 Apr 2025 22:16:30 GMT
• Title: THOUGHTTERMINATOR: Benchmarking, Calibrating, and Mitigating Overthinking in Reasoning Models
• Authors: Xiao Pu, Michael Saxon, Wenyue Hua, William Yang Wang,
• Abstract summary: We introduce approximate measures of problem-level difficulty and demonstrate that a clear relationship between problem difficulty and optimal token spend exists.<n>We find that in general, reasoning models are poorly calibrated, particularly on easy problems.<n>We introduce THOUGHTTERMINATOR, a training-free black box decoding technique that significantly improves reasoning model calibration.
• Score: 65.39456695678713
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reasoning models have demonstrated impressive performance on difficult tasks that traditional language models struggle at. However, many are plagued with the problem of overthinking--generating large amounts of unnecessary tokens which don't improve accuracy on a question. We introduce approximate measures of problem-level difficulty and demonstrate that a clear relationship between problem difficulty and optimal token spend exists, and evaluate how well calibrated a variety of reasoning models are in terms of efficiently allocating the optimal token count. We find that in general, reasoning models are poorly calibrated, particularly on easy problems. To evaluate calibration on easy questions we introduce DUMB500, a dataset of extremely easy math, reasoning, code, and task problems, and jointly evaluate reasoning model on these simple examples and extremely difficult examples from existing frontier benchmarks on the same task domain. Finally, we introduce THOUGHTTERMINATOR, a training-free black box decoding technique that significantly improves reasoning model calibration.

Related papers

• Climbing the Ladder of Reasoning: What LLMs Can-and Still Can't-Solve after SFT? [59.418994222096885]
  We conduct a detailed analysis of model performance on the AIME24 dataset.<n>We categorize questions into four tiers (Easy, Medium, Hard, and Extremely Hard)<n>We find that progression from Easy to Medium tier requires adopting an R1 reasoning style with minimal SFT-1K instances.<n>Exh-level questions present a fundamentally different challenge; they require unconventional problem-solving skills.
  arXiv  Detail & Related papers  (2025-04-16T03:39:38Z)
• DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models [31.189242663680695]
  This paper introduces Difficulty-Adaptive Slow-Thinking (DAST), a novel framework that enables models to autonomously adjust the length of Chain-of-Thought(CoT) based on problem difficulty.<n>Experiments on diverse datasets and model scales demonstrate that DAST effectively mitigates overthinking while preserving reasoning accuracy on complex problems.
  arXiv  Detail & Related papers  (2025-03-06T14:23:06Z)
• FINEREASON: Evaluating and Improving LLMs' Deliberate Reasoning through Reflective Puzzle Solving [90.88021670297664]
  FINEREASON is a logic-puzzle benchmark for evaluation of large language models' reasoning capabilities. We introduce two tasks: state checking, and state transition, for a comprehensive evaluation of how models assess the current situation and plan the next move. We show that models trained on our state checking and transition data demonstrate gains in math reasoning by up to 5.1% on GSM8K.
  arXiv  Detail & Related papers  (2025-02-27T16:23:25Z)
• Large Language Models and Mathematical Reasoning Failures [1.6114012813668932]
  This paper investigates the mathematical reasoning capabilities of large language models (LLMs) using 50 newly constructed high-school-level word problems. We rigorously analyze both final answers and solution steps to identify reasoning failures. We find that while newer models (e.g., o3-mini, deepseek-r1) achieve higher accuracy, all models exhibit errors in spatial reasoning, strategic planning, and arithmetic.
  arXiv  Detail & Related papers  (2025-02-17T09:07:32Z)
• MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations [90.07275414500154]
  We observe significant performance drops on MATH-P-Hard across various models. We also raise concerns about a novel form of memorization where models blindly apply learned problem-solving skills.
  arXiv  Detail & Related papers  (2025-02-10T13:31:46Z)
• ProcessBench: Identifying Process Errors in Mathematical Reasoning [62.80402845414901]
  We introduce ProcessBench for measuring the ability to identify erroneous steps in mathematical reasoning.<n>ProcessBench consists of 3,400 test cases, primarily focused on competition- and Olympiad-level math problems.<n>We conduct extensive evaluation on ProcessBench, involving two types of models: process reward models (PRMs) and critic models.
  arXiv  Detail & Related papers  (2024-12-09T15:11:40Z)
• Subtle Errors Matter: Preference Learning via Error-injected Self-editing [59.405145971637204]
  We propose a novel preference learning framework called eRror-Injected Self-Editing (RISE)<n>RISE injects predefined subtle errors into pivotal tokens in reasoning or steps to construct hard pairs for error mitigation.<n>Experiments validate the effectiveness of RISE, with preference learning on Qwen2-7B-Instruct yielding notable improvements of 3.0% on GSM8K and 7.9% on MATH with only 4.5K training samples.
  arXiv  Detail & Related papers  (2024-10-09T07:43:38Z)
• Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Models [13.532180752491954]
  Large Language Models (LLMs) are often described as instances of foundation models that possess strong generalization obeying scaling laws.<n>We demonstrate here a dramatic breakdown of generalization and basic reasoning of all SOTA models claiming strong function.<n>We also observe strong overconfidence in the wrong solutions, expressed in form of plausible sounding explanation-like confabulations.
  arXiv  Detail & Related papers  (2024-06-04T07:43:33Z)
• CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs' Mathematical Reasoning Capabilities [25.857946070979576]
  Concept and Hint-Annotated Math Problems (CHAMP) consists of high school math competition problems annotated with concepts. This benchmark is difficult, with the best model only scoring 58.1% in standard settings. We find that models often arrive at the correct final answer through wrong reasoning steps.
  arXiv  Detail & Related papers  (2024-01-13T03:18:16Z)
• GRACE: Discriminator-Guided Chain-of-Thought Reasoning [75.35436025709049]
  We propose Guiding chain-of-thought ReAsoning with a CorrectnEss Discriminator (GRACE) to steer the decoding process towards producing correct reasoning steps. GRACE employs a discriminator trained with a contrastive loss over correct and incorrect steps, which is used during decoding to score next-step candidates.
  arXiv  Detail & Related papers  (2023-05-24T09:16:51Z)
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness [68.97830259849086]
  Most datasets only capture a simpler subproblem and likely suffer from spurious features. We study adversarial robustness - a local generalization property - to reveal hard, model-specific instances and spurious features. Unlike in other applications, where perturbation models are designed around subjective notions of imperceptibility, our perturbation models are efficient and sound. Surprisingly, with such perturbations, a sufficiently expressive neural solver does not suffer from the limitations of the accuracy-robustness trade-off common in supervised learning.
  arXiv  Detail & Related papers  (2021-10-21T07:28:11Z)

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.