Trustworthy-ML-Lab / ThinkEditLinks
[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.
☆15Updated 3 weeks ago
Alternatives and similar repositories for ThinkEdit
Users that are interested in ThinkEdit are comparing it to the libraries listed below
Sorting:
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆44Updated 6 months ago
- The implementation of paper "On Reasoning Strength Planning in Large Reasoning Models"☆25Updated 3 months ago
- A Sober Look at Language Model Reasoning☆85Updated 2 weeks ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆79Updated 4 months ago
- [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"☆37Updated 3 months ago
- ☆53Updated 2 years ago
- [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆20Updated 6 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆93Updated 8 months ago
- ☆54Updated 3 months ago
- ☆18Updated last year
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆85Updated 6 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆80Updated 10 months ago
- ☆66Updated last year
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆51Updated last year
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆32Updated 7 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆47Updated 11 months ago
- ☆63Updated 7 months ago
- Codebase for decoding compressed trust.☆24Updated last year
- Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic☆30Updated last month
- ☆67Updated 6 months ago
- ☆28Updated 7 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆157Updated 6 months ago
- Code for paper: Aligning Large Language Models with Representation Editing: A Control Perspective☆34Updated 8 months ago
- This is the official code for the paper "Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable".☆26Updated 7 months ago
- 📜 Paper list on decoding methods for LLMs and LVLMs☆61Updated 3 months ago
- The official repository of NeurIPS'25 paper "Ada-R1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆19Updated last month
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆186Updated 3 months ago
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆20Updated 6 months ago
- ☆51Updated last year
- [NeurIPS25] Official repo for "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"☆33Updated 3 weeks ago