Pith. sign in

REVIEW 8 cited by

Evaluating Mathematical Reasoning Beyond Accuracy

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.05692 v2 pith:QXDH4M6W submitted 2024-04-08 cs.CL

classification cs.CL
keywords reasonevalreasoningmathematicalqualitystepsaccuracyllmsbeyond
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The leaderboard of Large Language Models (LLMs) in mathematical tasks has been continuously updated. However, the majority of evaluations focus solely on the final results, neglecting the quality of the intermediate steps. This oversight can mask underlying problems, such as logical errors or unnecessary steps in the reasoning process. To measure reasoning beyond final-answer accuracy, we introduce ReasonEval, a new methodology for evaluating the quality of reasoning steps. ReasonEval employs validity and redundancy to characterize the reasoning quality, as well as accompanying LLMs to assess them automatically. We explore different design options for the LLM-based evaluators and empirically demonstrate that ReasonEval, when instantiated with base models possessing strong mathematical knowledge and trained with high-quality labeled data, consistently outperforms baseline methods in the meta-evaluation datasets. We also highlight the strong generalization capabilities of ReasonEval. By utilizing ReasonEval to evaluate LLMs specialized in math, we find that an increase in final-answer accuracy does not necessarily guarantee an improvement in the overall quality of the reasoning steps for challenging mathematical problems. Additionally, we observe that ReasonEval can play a significant role in data selection. We open-source the best-performing model, meta-evaluation script, and all evaluation results to facilitate future research.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. MedPRMBench: A Fine-grained Benchmark for Process Reward Models in Medical Reasoning

    cs.CL 2026-04 unverdicted novelty 8.0 of 10

    MedPRMBench is the first fine-grained benchmark for process reward models in medical reasoning, featuring 6500 questions, 13000 chains, 113910 step labels, and a baseline that improves downstream QA accuracy by 3.2-6....

  2. CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning

    cs.CL 2025-07 unverdicted novelty 6.0 of 10

    CoLD mitigates length bias in process reward models for mathematical reasoning via counterfactual guidance, length penalties, bias estimation, and joint training, improving step selection accuracy and conciseness on M...

  3. ZeroSearch: Incentivize the Search Capability of LLMs without Searching

    cs.CL 2025-05 conditional novelty 6.0 of 10

    ZeroSearch simulates search engine interactions via supervised fine-tuning of a retrieval module and curriculum-based RL degradation of document quality, achieving comparable or superior performance to real search eng...

  4. ZeroSearch: Incentivize the Search Capability of LLMs without Searching

    cs.CL 2025-05 unverdicted novelty 6.0 of 10

    ZeroSearch uses supervised fine-tuning to create a simulated retrieval module and curriculum-based RL rollouts that degrade document quality to train LLMs on search capabilities without real search API calls.

  5. The Lessons of Developing Process Reward Models in Mathematical Reasoning

    cs.CL 2025-01 unverdicted novelty 6.0 of 10

    Monte Carlo data synthesis for PRMs underperforms LLM-judge and human methods, Best-of-N evaluations suffer from process-outcome misalignment and score inflation, and consensus filtering yields better PRMs with higher...

  6. Search-o1: Agentic Search-Enhanced Large Reasoning Models

    cs.AI 2025-01 unverdicted novelty 6.0 of 10

    Search-o1 integrates agentic retrieval-augmented generation and a Reason-in-Documents module into large reasoning models to dynamically supply missing knowledge and improve performance on complex science, math, coding...

  7. Argumentative Large Language Models for Explainable and Contestable Claim Verification

    cs.CL 2024-05 unverdicted novelty 6.0 of 10

    ArgLLMs build argumentation frameworks from LLMs to support explainable and contestable formal reasoning for claim verification.

  8. LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods

    cs.CL 2024-12 accept novelty 3.0 of 10

    A survey that organizes LLMs-as-judges research into functionality, methodology, applications, meta-evaluation, and limitations.

Pith tools