Tong Niu

JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking

Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification

Parameter-Efficient Detoxification with Contrastive Decoding

DivKnowQA: Verifying the Reasoning Ability of LLM Through Open-Domain Question Answering Over Knowledge Base and Text

Complex QA with Diverse Knowledge Sources: Novel Benchmark and Approach