9 papers
AgentV-RL: Scaling Reward Modeling with Agentic Verifier
Jiazheng Zhang, Ziche Fu, Zhiheng Xi +13
Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect in…
Make LoRA Great Again: Boosting LoRA with Adaptive Singular Values and Mixture-of-Experts Optimization Alignment
Chenghao Fan, Zhenyi Lu, Sichen Liu +4
While Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning for Large Language Models (LLMs), its performance often falls short of Full Fine-Tuning (Full FT). Current…
Stable-DiffCoder: Pushing the Frontier of Code Diffusion Large Language Model
Chenghao Fan, Wen Heng, Bo Li +6
Diffusion-based language models (DLLMs) offer non-sequential, block-wise generation and richer data reuse compared to autoregressive (AR) models, but existing code DLLMs still lag…
Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language Models
Zhuojun Ding, Wei Wei, Chenghao Fan
Supervised fine-tuning (SFT) is widely used to align large language models (LLMs) with information extraction (IE) tasks, such as named entity recognition (NER). However, annotatin…
Chinese-Vicuna: A Chinese Instruction-following Llama-based Model
Chenghao Fan, Zhenyi Lu, Jie Tian
Chinese-Vicuna is an open-source, resource-efficient language model designed to bridge the gap in Chinese instruction-following capabilities by fine-tuning Meta's LLaMA architectur…
On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
Chenghao Fan, Zhenyi Lu, Wei Wei +4
Efficient fine-tuning of large language models for task-specific applications is imperative, yet the vast number of parameters in these models makes their training increasingly cha…