tongjingqi / MathTrapLinks
In this work, we investigate the compositionality of large language models (LLMs) in mathematical reasoning. Specifically, we construct a new dataset MATHTRAP‡ by introducing carefully designed logical traps into the problem descriptions of MATH and GSM8K.
☆61Updated 9 months ago
Alternatives and similar repositories for MathTrap
Users that are interested in MathTrap are comparing it to the libraries listed below
Sorting:
- Generative AI Act II: Test Time Scaling Drives Cognition Engineering☆209Updated 7 months ago
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆254Updated 4 months ago
- A Framework for LLM-based Multi-Agent Reinforced Training and Inference☆373Updated last month
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆235Updated last week
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆269Updated last year
- 😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, Agent, and Beyond☆319Updated 2 months ago
- A version of verl to support diverse tool use☆745Updated last week
- Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning☆121Updated last week
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆388Updated 2 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆71Updated 8 months ago
- Curation of resources for LLM research, screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise de…☆63Updated last year
- A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical …☆49Updated 3 months ago
- A comprehensive collection of process reward models.☆127Updated 2 months ago
- ☆213Updated 10 months ago
- Implementation for the research paper "Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision".☆56Updated last year
- a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation☆61Updated 8 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆141Updated last month
- ☆319Updated 6 months ago
- This is the repository of DEER, a Dynamic Early Exit in Reasoning method for Large Reasoning Language Models.☆177Updated 5 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆258Updated 7 months ago
- A series of technical report on Slow Thinking with LLM☆751Updated 4 months ago
- 🔥 How to efficiently and effectively compress the CoTs or directly generate concise CoTs during inference while maintaining the reasonin…☆64Updated 6 months ago
- Latest Advances on Long Chain-of-Thought Reasoning☆573Updated 5 months ago
- ☆292Updated 5 months ago
- [TMLR 2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models☆707Updated 2 months ago
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆145Updated last month
- ☆249Updated 4 months ago
- ☆70Updated 8 months ago
- Extrapolating RLVR to General Domains without Verifiers☆184Updated 4 months ago
- ☆329Updated 6 months ago