Tebmer/Rereading-LLM-Reasoning
EMNLP 2024 "Re-reading improves reasoning in large language models". Simply repeating the question to get bidirectional understanding for improving reasoning.
This project helps anyone using Large Language Models (LLMs) to improve the accuracy of their reasoning tasks, especially with complex questions. By simply re-presenting the initial question to the LLM, the system generates more accurate and consistent answers. The target users are researchers, data scientists, or practitioners who build or evaluate LLM-powered applications and need to boost their models' problem-solving capabilities without complex retraining.
No commits in the last 6 months.
Use this if you are working with Large Language Models and find them struggling with complex reasoning problems or providing inconsistent answers, and you want a straightforward method to improve their accuracy.
Not ideal if your primary goal is to optimize model inference speed for simple tasks, as the "re-reading" step adds a slight processing overhead.
Stars
29
Forks
3
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 10, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Tebmer/Rereading-LLM-Reasoning"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvs-health/uqlm
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM...
PRIME-RL/TTRL
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
sapientinc/HRM
Hierarchical Reasoning Model Official Release
tigerchen52/query_level_uncertainty
query-level uncertainty in LLMs
reasoning-survey/Awesome-Reasoning-Foundation-Models
✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models