Picture for Shizhe Diao

Shizhe Diao

CodeGraph: Enhancing Graph Reasoning of LLMs with Code

Add code
Aug 25, 2024
Viaarxiv icon

FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation

Add code
Aug 22, 2024
Viaarxiv icon

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts

Add code
Jul 03, 2024
Viaarxiv icon

VeraCT Scan: Retrieval-Augmented Fake News Detection with Justifiable Reasoning

Add code
Jun 12, 2024
Viaarxiv icon

PLUM: Preference Learning Plus Test Cases Yields Better Code Language Models

Add code
Jun 11, 2024
Viaarxiv icon

SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales

Add code
May 31, 2024
Viaarxiv icon

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

Add code
Mar 28, 2024
Viaarxiv icon

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards

Add code
Mar 06, 2024
Viaarxiv icon

Can We Verify Step by Step for Incorrect Answer Detection?

Add code
Feb 16, 2024
Viaarxiv icon

The Instinctive Bias: Spurious Images lead to Hallucination in MLLMs

Add code
Feb 06, 2024
Viaarxiv icon