Pith. sign in

REVIEW 13 cited by

InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning

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 2402.06332 v2 pith:IARYJM3F submitted 2024-02-09 cs.CL

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

The math abilities of large language models can represent their abstract reasoning ability. In this paper, we introduce and open-source our math reasoning LLMs InternLM-Math which is continue pre-trained from InternLM2. We unify chain-of-thought reasoning, reward modeling, formal reasoning, data augmentation, and code interpreter in a unified seq2seq format and supervise our model to be a versatile math reasoner, verifier, prover, and augmenter. These abilities can be used to develop the next math LLMs or self-iteration. InternLM-Math obtains open-sourced state-of-the-art performance under the setting of in-context learning, supervised fine-tuning, and code-assisted reasoning in various informal and formal benchmarks including GSM8K, MATH, Hungary math exam, MathBench-ZH, and MiniF2F. Our pre-trained model achieves 30.3 on the MiniF2F test set without fine-tuning. We further explore how to use LEAN to solve math problems and study its performance under the setting of multi-task learning which shows the possibility of using LEAN as a unified platform for solving and proving in math. Our models, codes, and data are released at \url{https://github.com/InternLM/InternLM-Math}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

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

  1. SocietyBench: Forecasting Counterfactual Social-World Evolution

    cs.CL 2026-08 conditional novelty 7.0 of 10

    A new benchmark measures LLM social-world forecasting on anonymized real events, finding the best model reaches 75/100 and agent scaffolding does not help.

  2. From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontier

    cs.CL 2026-07 accept novelty 6.0 of 10

    LLM formal provers must shift from competition solvers to research agents that handle open-ended, under-specified frontier mathematics under machine-checked rigor.

  3. LeanTree: Accelerating White-Box Proof Search with Factorized States in Lean 4

    cs.LG 2025-07 conditional novelty 6.0 of 10

    White-box proof search with factorized Lean 4 goals reaches 18.4% on MiniF2F with Llemma-7B, outperforming black-box generation at 9.6%.

  4. Generalized Tree Edit Distance (GTED): A Faithful Evaluation Metric for Statement Autoformalization

    cs.LG 2025-07 conditional novelty 6.0 of 10

    GTED uses tree edit distance on operator trees of standardized Lean statements to evaluate autoformalization, ranking top on miniF2F and joint-top on ProofNet.

  5. VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement Learning

    cs.MM 2025-07 conditional novelty 6.0 of 10

    VRAgent-R1 uses an MLLM agent to summarize videos and a reinforcement-learned agent to simulate user choices, improving video recommendation and user-decision simulation on MicroLens-100K.

  6. Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A 7B LLM trained with sparse completion rewards and a GRPO-style algorithm reaches state-of-the-art on ALFWorld and ScienceWorld.

  7. Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification

    cs.CL 2025-06 conditional novelty 6.0 of 10

    Safe uses step-level formal verification in Lean 4, aggregated by a small LSTM and combined with process reward scores, to improve best-of-n accuracy for LLM mathematical reasoning.

  8. Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery

    cs.AI 2026-06 unverdicted novelty 5.0 of 10

    An integrated survey organizing AI mathematical reasoning into informal, formal, discovery, and technique axes while cataloging benchmarks and assessing failure modes.

  9. A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data

    cs.AI 2026-01 conditional novelty 5.0 of 10

    A metric-oriented survey that classifies intrinsic quality and trustworthiness metrics for LLM-generated data across six modalities and documents systematic evaluation gaps in the current literature.

  10. Integrating Rules and Semantics for LLM-Based C-to-Rust Translation

    cs.SE 2025-08 unverdicted novelty 5.0 of 10

    IRENE combines rule-based retrieval, structured summarization, and compiler feedback to improve LLM-based C-to-Rust translation accuracy and safety.

  11. LeanConjecturer: Automatic Generation of Mathematical Conjectures for Theorem Proving

    cs.AI 2025-06 conditional novelty 5.0 of 10

    LeanConjecturer automatically generates thousands of Lean 4 theorem statements from Mathlib files and uses them for reinforcement learning, with modest measured gains on held-out problems.

  12. Formally Solving Answer-Construction Problems in Lean

    cs.AI 2025-05 reject novelty 5.0 of 10

    ECP, an enumerate-conjecture-prove framework with Lean verification, improves answer-construction accuracy on ConstructiveBench and a PutnamBench subset, but its benchmark has a 17% major-error rate and its abstract r...

  13. UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning

    cs.CV 2025-05 conditional novelty 5.0 of 10

    UniVG-R1 uses CoT supervised fine-tuning plus GRPO with difficulty-aware reweighting to make Qwen2-VL substantially better at multi-image, reasoning-based visual grounding.

Pith tools