VietHoang1512/PSR

Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection (EMNLP 2025 Findings)

stars

commits

Python

primary language

Jul 2, 2025

updated

README

Code for the paper "Think Twice, Generate Once: Enhancing LLMs Safety via Progressive Self-Reflection"

4 commits

ouhenio/llms-overstimate-profoundness

xu1998hz/llm_self_bias

This is the project to quantify the issues with LLM's self evaluation

ziyaow1010/Reasoning_Length_Prediction

niez233/DLLM_safety

dsshay/CodePatchLLM

Extension for any LLM that utilizes Svace feedback for code generation

SeungyounShin/SPIN

Unofficial implementation of Self-Play Fine-Tuning Converts Weak Language Models to Strong Language…

ruipeterpan/failfast

Artifact for "Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via…

tigerchen52/reconfidencing_llms

Python

79.7%

Shell

20.3%