mlsanityData to 7 Oct 2026

Over-Reasoning and Redundant Calculation of Large Language Models

arXiv 2401.11467 ↗First posted 21 Jan 2024cs.CLcited by 27

On the map: LLM reasoning → Mathematical reasoning

Abstract (arXiv)

Large language models (LLMs) can solve problems step-by-step. While this chain-of-thought (CoT) reasoning boosts LLMs' performance, it is unclear if LLMs textitknow when to use CoT and whether those CoT are always necessary to answer the question. This paper shows that LLMs tend to generate redundant calculations and reasoning on a manually constructed math QA dataset, GSM8K-Zero. GSM8K-Zero is constructed such that the questions can be answered without any calculations, but LLMs, including Llama-2 models and Claude-2, tend to generate lengthy and unnecessary calculations to answer the questions. We also conduct experiments to explain why LLMs generate redundant calculations and reasonings. GSM8K-Zero is publicly available at https://github.com/d223302/Over-Reasoning-of-LLMs and https://huggingface.co/datasets/dcml0714/GSM8K-Zero.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Placed in Mathematical reasoning, one of 17 directions in LLM reasoning. Builds on 7 of its 19 references that are in the map. First posted on arXiv 21 Jan 2024.

Builds on

7 of 19 references.

References · 7

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2023PaLM 2 Technical Reportcited by 1,154
  6. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  7. 2023How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detectioncited by 472

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 15; 2026: 7.

27 papers.

Sort:

By area:

  1. 2025Self-Training Elicits Concise Reasoning in Large Language Modelscited by 97
  2. 2025How Well do LLMs Compress Their Own Chain-of-Thought? A Token Complexity Approachcited by 95
  3. 2025Evaluating Step-by-step Reasoning Traces: A Surveycited by 62
  4. 2025Efficient Inference for Large Reasoning Models: A Surveycited by 58
  5. 2024How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?cited by 44
  6. 2025Oolong: Evaluating Long Context Reasoning and Aggregation Capabilitiescited by 33
  7. 2024Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Coursecited by 19
  8. 2025Lost at the Beginning of Reasoningcited by 15
  9. 2025Stop When Enough: Adaptive Early-Stopping for Chain-of-Thought Reasoningcited by 15
  10. 2025Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Promptingcited by 13
  11. 2024Verbosity neq Veracity: Demystify Verbosity Compensation Behavior of Large Language Modelscited by 5
  12. 2025FormalML: A Benchmark for Evaluating Formal Subgoal Completion in Machine Learning Theorycited by 5
15 more
  1. 2026Do Chatbot LLMs Talk Too Much? The YapBench Benchmarkcited by 5
  2. 2025When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Modelscited by 4
  3. 2026CoTJudger: A Graph-Driven Framework for Automatic Evaluation of Chain-of-Thought Efficiency and Redundancy in LRMscited by 3
  4. 2024Attention Overflow: Language Model Input Blur during Long-Context Missing Items Recommendationcited by 2
  5. 2025From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinementcited by 2
  6. 2025ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Modelscited by 1
  7. 2025Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Informationcited by 1
  8. 2025Explainable reinforcement learning from human feedback to improve alignmentcited by 1
  9. 2026Judge Model for Large-scale Multimodality Benchmarkscited by 1
  10. 2026Think Less, Know More: State-Aware Reasoning Compression with Knowledge Guidance for Efficient Reasoningcited by 1
  11. 2026CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruningcited by 1
  12. 2024Did You Hear That? Introducing AADG: A Framework for Generating Benchmark Data in Audio Anomaly Detectioncited by 0
  13. 2025Adaptive Reasoning Executor: A Collaborative Agent System for Efficient Reasoningcited by 0
  14. 2026The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world modelscited by 0
  15. 2026Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Do LLMs Overthink Basic Math Reasoning? Benchmarking the Accuracy-Efficiency Tradeoff in Language Models
  2. 2024LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics
  3. 2025Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation
  4. 2025LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!
  5. 2024GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models
  6. 2025Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges
  7. 2024Evaluating Mathematical Reasoning of Large Language Models: A Focus on Error Identification and Correction
  8. 2025Large Language Models and Mathematical Reasoning Failures