9 papers
Improving Value-based Process Verifier via Low-Cost Variance Reduction
Zetian Sun, Dongfang Li, Baotian Hu +1
Large language models (LLMs) have achieved remarkable success in a wide range of tasks. However, their reasoning capabilities, particularly in complex domains like mathematics, rem…
Is On-Policy Data always the Best Choice for Direct Preference Optimization-based LM Alignment?
Zetian Sun, Dongfang Li, Xuhui Chen +2
The alignment of language models~(LMs) with human preferences is critical for building reliable AI systems. The problem is typically framed as optimizing an LM policy to maximize t…
Improving Value-based Process Verifier via Structural Prior Injection
Zetian Sun, Dongfang Li, Baotian Hu +2
In the Large Language Model(LLM) reasoning scenario, people often estimate state value via Monte Carlo sampling. Though Monte Carlo estimation is an elegant method with less induct…
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Xinping Zhao, Xinshuo Hu, Zifei Shan +14
Recent advancements in Large Language Models (LLMs)-based text embedding models primarily focus on data scaling or synthesis, yet limited exploration of training techniques and dat…
Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
Zetian Sun, Dongfang Li, Zhuoen Chen +2
Reward sparsity in long-horizon reinforcement learning (RL) tasks remains a significant challenge, while existing outcome-based reward shaping struggles to define meaningful immedi…
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
Xinping Zhao, Yan Zhong, Zetian Sun +5
Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful…