Trustworthy-ML-Lab/ThinkEdit

[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.

25
/ 100
Experimental

This project helps improve the performance of large language models (LLMs) on complex reasoning tasks by addressing overly short reasoning. It takes an existing LLM's responses to problems and identifies specific internal components responsible for insufficient 'thinking' steps. The output is a modified LLM that generates more complete and accurate reasoning, benefiting anyone using LLMs for tasks requiring detailed, multi-step problem-solving.

Use this if your LLM is producing correct answers on mathematical or logical problems but often skips intermediate steps, leading to less reliable or less transparent results.

Not ideal if you need to debug or modify an LLM's behavior for issues unrelated to reasoning length, such as factual inaccuracies, stylistic preferences, or ethical concerns.

LLM fine-tuning reasoning improvement mathematical problem solving interpretability AI model enhancement
No License No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

Python

License

Last pushed

Dec 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Trustworthy-ML-Lab/ThinkEdit"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.