[EMNLP 25] An effective and interpretable weight-editing method for mitigating overly short reasoning in LLMs, and a mechanistic study uncovering how reasoning length is encoded in the model’s representation space.
☆17Dec 17, 2025Updated 2 months ago
Alternatives and similar repositories for ThinkEdit
Users that are interested in ThinkEdit are comparing it to the libraries listed below
Sorting:
- [COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆52Apr 6, 2025Updated 10 months ago
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆21Nov 9, 2025Updated 3 months ago
- Inverse Scaling in Test-Time Compute☆25Dec 3, 2025Updated 2 months ago
- Official implementation for "Mixture of In-Context Experts Enhance LLMs’ Awareness of Long Contexts" (Accepted by Neurips2024)☆13Jan 7, 2025Updated last year
- ☆13Jan 15, 2025Updated last year
- ☆15Feb 26, 2025Updated last year
- An extention to the GaLore paper, to perform Natural Gradient Descent in low rank subspace☆18Oct 21, 2024Updated last year
- ☆32Nov 11, 2024Updated last year
- ☆82Nov 11, 2024Updated last year
- [NeurIPS 2024 Main Track] Code for the paper titled "Instruction Tuning With Loss Over Instructions"☆38May 24, 2024Updated last year
- Preparing for ML Interviews.☆54Jan 12, 2026Updated last month
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆92Feb 14, 2025Updated last year
- [ACL 2025] An inference-time decoding strategy with adaptive foresight sampling☆108May 18, 2025Updated 9 months ago
- ☆10Oct 29, 2020Updated 5 years ago
- ☆11Oct 25, 2024Updated last year
- Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity☆22Aug 28, 2025Updated 6 months ago
- ☆10Jul 8, 2021Updated 4 years ago
- ☆13Jun 25, 2025Updated 8 months ago
- Influence Maximization Paper List☆11May 11, 2022Updated 3 years ago
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆12Oct 31, 2024Updated last year
- Code for paper "Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion"☆14Mar 28, 2024Updated last year
- Code for paper "Towards Efficient Pareto Set Approximation via Weight-Ensembling Mixture of Experts"☆11Sep 13, 2024Updated last year
- Source code and data of our paper "Missing Counter-Evidence Renders NLP Fact-Checking Unrealistic for Misinformation" (https://arxiv.org/…☆10Jun 21, 2023Updated 2 years ago
- [ICML 2024] Code for the paper "MoE-RBench: Towards Building Reliable Language Models with Sparse Mixture-of-Experts"☆10Jul 1, 2024Updated last year
- Official implementation for Text Generation Beyond Discrete Token Sampling☆21Aug 11, 2025Updated 6 months ago
- Explanation Optimization☆13Oct 16, 2020Updated 5 years ago
- The code implementation of MuScleLoRA (Accepted in ACL 2024)☆10Dec 1, 2024Updated last year
- Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure (NeurIPS 2024) + Arithmetic Transfor…☆14Oct 26, 2025Updated 4 months ago
- Reproduction of "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization" for the Reproducibility challenge@NeurIPS…☆11Jan 14, 2020Updated 6 years ago
- [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications☆52Oct 30, 2025Updated 4 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Aug 14, 2024Updated last year
- ☆54Oct 29, 2024Updated last year
- Quantum Hamiltonian Descent: numerical simulation, real-machine deployment, and benchmarking☆11Jan 16, 2024Updated 2 years ago
- An Ultra-Long Output Reinforcement Learning Approach☆23Jul 31, 2025Updated 7 months ago
- [ICLR 2022] "Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How" by Yuning You, Yue Cao, Tianl…☆14Aug 19, 2022Updated 3 years ago
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆13Apr 17, 2025Updated 10 months ago
- [NeurIPS25] RULE: Reinforcement UnLEarning Achieves Forge-retain Pareto Optimality☆19Oct 22, 2025Updated 4 months ago
- ☆11Jan 24, 2022Updated 4 years ago
- Official codes for COLING 2024 paper "Robust and Scalable Model Editing for Large Language Models": https://arxiv.org/abs/2403.17431v1☆14Mar 27, 2024Updated last year