5 papers
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
Xiaofan Li, Ming Yang, Zhiyuan Ma +9
Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant advances in the reasoning capabilities of Large Language Models (LLMs). However, effectively managin…
TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization
Shichao Ma, Zhiyuan Ma, Ming Yang +8
Multi-turn tool-integrated reasoning enables Large Language Models (LLMs) to solve complex tasks through iterative information retrieval. However, current reinforcement learning (R…
Training LLMs to be Better Text Embedders through Bidirectional Reconstruction
Chang Su, Dengliang Shi, Siyuan Huang +5
Large language models (LLMs) have increasingly been explored as powerful text embedders. Existing LLM-based text embedding approaches often leverage the embedding of the final toke…
Mirror-Consistency: Harnessing Inconsistency in Majority Voting
Siyuan Huang, Zhiyuan Ma, Jintao Du +3
Self-Consistency, a widely-used decoding strategy, significantly boosts the reasoning capabilities of Large Language Models (LLMs). However, it depends on the plurality voting rule…
Gumbel Reranking: Differentiable End-to-End Reranker Optimization
Siyuan Huang, Zhiyuan Ma, Jintao Du +5
RAG systems rely on rerankers to identify relevant documents. However, fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs. Existing…