zjunlp / LightThinkerLinks
LightThinker: Thinking Step-by-Step Compression
☆61Updated 3 months ago
Alternatives and similar repositories for LightThinker
Users that are interested in LightThinker are comparing it to the libraries listed below
Sorting:
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆74Updated last month
- [ACL-25] We introduce ScaleQuest, a scalable, novel and cost-effective data synthesis method to unleash the reasoning capability of LLMs.☆63Updated 8 months ago
- Revisiting Mid-training in the Era of Reinforcement Learning Scaling☆137Updated this week
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆80Updated 6 months ago
- General Reasoner: Advancing LLM Reasoning Across All Domains☆147Updated last month
- [ICML 2025] Teaching Language Models to Critique via Reinforcement Learning☆102Updated 2 months ago
- Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]☆163Updated this week
- The official repository of the Omni-MATH benchmark.☆85Updated 6 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆211Updated 4 months ago
- [AAAI 2025 oral] Evaluating Mathematical Reasoning Beyond Accuracy☆63Updated 6 months ago
- [ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆77Updated 7 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆125Updated 3 months ago
- RL Scaling and Test-Time Scaling (ICML'25)☆108Updated 5 months ago
- SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis☆79Updated last month
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆114Updated last year
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆226Updated last month
- RM-R1: Unleashing the Reasoning Potential of Reward Models☆113Updated 2 weeks ago
- A unified suite for generating elite reasoning problems and training high-performance LLMs, including pioneering attention-free architect…☆63Updated last month
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆62Updated last year
- Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"☆165Updated last month
- Large Language Models Can Self-Improve in Long-context Reasoning☆71Updated 7 months ago
- [NAACL 2024 Outstanding Paper] Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't…☆114Updated last year
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆105Updated 4 months ago
- LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models☆76Updated 8 months ago
- ☆122Updated last month
- [ICLR 2025] SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction☆74Updated 3 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆71Updated last month
- A version of verl to support tool use☆288Updated this week
- [ICLR 2025] 🧬 RegMix: Data Mixture as Regression for Language Model Pre-training (Spotlight)☆151Updated 4 months ago
- ☆59Updated 10 months ago