Trustworthy-ML-Lab / ThinkEditLinks
An effective 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.
☆12Updated 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☆39Updated 4 months ago
- The implementation of paper "On Reasoning Strength Planning in Large Reasoning Models"☆20Updated last month
- [ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆81Updated 4 months ago
- Official repository for paper: O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning☆86Updated 5 months ago
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆47Updated 9 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆71Updated 7 months ago
- Official code for Guiding Language Model Math Reasoning with Planning Tokens☆14Updated last year
- Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic☆27Updated 6 months ago
- A Sober Look at Language Model Reasoning☆81Updated last month
- ☆20Updated 8 months ago
- This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)☆45Updated 8 months ago
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆20Updated 3 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆143Updated 3 months ago
- Codebase for decoding compressed trust.☆24Updated last year
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆75Updated last month
- ☆44Updated last year
- The official repository of paper "AdaR1: From Long-Cot to Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization"☆18Updated 3 months ago
- Github Repo for OATS: Outlier-Aware Pruning through Sparse and Low Rank Decomposition☆13Updated 3 months ago
- ☆23Updated 4 months ago
- [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"☆35Updated 2 weeks ago
- ☆15Updated 11 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆43Updated 3 weeks ago
- This is the official code for the paper "Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturba…☆29Updated 4 months ago
- [ACL 25] SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities☆18Updated 4 months ago
- ☆65Updated 3 months ago
- ☆60Updated last year
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆171Updated last month
- ThinK: Thinner Key Cache by Query-Driven Pruning☆22Updated 5 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆103Updated 3 weeks ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆23Updated 10 months ago