10 papers
AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection
Peng Lai, He Zhu, Zhiwen Ruan +6
Aligning large language models with human preferences remains a challenge, primarily due to the critical role of preference data quality in effective alignment. Existing datasets a…
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
Zhiwen Ruan, Yichao Du, Jianjie Zheng +6
A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tu…
Evaluating Memory Capability in Continuous Lifelog Scenario
Jianjie Zheng, Zhichen Liu, Zhanyu Shen +6
Nowadays, wearable devices can continuously lifelog ambient conversations, creating substantial opportunities for memory systems. However, existing benchmarks primarily focus on on…
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
Tianyi Wang, Yixia Li, Long Li +6
Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in th…
InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning
Junyou Su, He Zhu, Xiao Luo +6
Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing returns. Existing data se…
G2: Guided Generation for Enhanced Output Diversity in LLMs
Zhiwen Ruan, Yixia Li, Yefeng Liu +5
Large Language Models (LLMs) have demonstrated exceptional performance across diverse natural language processing tasks. However, these models exhibit a critical limitation in outp…
Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
Zhiwen Ruan, Yixia Li, He Zhu +4
Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. How…
Unveiling Over-Memorization in Finetuning LLMs for Reasoning Tasks
Zhiwen Ruan, Yun Chen, Yutao Hou +3
The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the le…
FormaRL: Enhancing Autoformalization with no Labeled Data
Yanxing Huang, Xinling Jin, Sijie Liang +2
Autoformalization is one of the central tasks in formal verification, while its advancement remains hindered due to the data scarcity and the absence efficient methods. In this wor…
Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations
Peng Lai, Jianjie Zheng, Sijie Cheng +4
The growing scale of evaluation tasks has led to the widespread adoption of automated evaluation using LLMs, a paradigm known as "LLM-as-a-judge". However, improving its alignment…