95 citations · 307 across the 25 of their papers we have counts for
9 papers · 1 filter
Silkie: Preference Distillation for Large Visual Language Models
Lei Li, Zhihui Xie, Mukai Li +6
This paper explores preference distillation for large vision language models (LVLMs), improving their ability to generate helpful and faithful responses anchoring the visual contex…
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Peiyi Wang, Lei Li, Zhihong Shao +6
In this paper, we present an innovative process-oriented math process reward model called \textbf{Math-Shepherd}, which assigns a reward score to each step of math problem solution…
Guiding AMR Parsing with Reverse Graph Linearization
Bofei Gao, Liang Chen, Peiyi Wang +2
Abstract Meaning Representation (AMR) parsing aims to extract an abstract semantic graph from a given sentence. The sequence-to-sequence approaches, which linearize the semantic gr…
Not All Demonstration Examples are Equally Beneficial: Reweighting Demonstration Examples for In-Context Learning
Zhe Yang, Damai Dai, Peiyi Wang +1
Large Language Models (LLMs) have recently gained the In-Context Learning (ICL) ability with the models scaling up, allowing them to quickly adapt to downstream tasks with only a f…
Making Large Language Models Better Reasoners with Alignment
Peiyi Wang, Lei Li, Liang Chen +5
Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the…
MIT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning
Lei Li, Yuwei Yin, Shicheng Li +9
Instruction tuning has significantly advanced large language models (LLMs) such as ChatGPT, enabling them to align with human instructions across diverse tasks. However, progress i…
RepCL: Exploring Effective Representation for Continual Text Classification
Yifan Song, Peiyi Wang, Dawei Zhu +3
Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classificatio…
Enhancing Continual Relation Extraction via Classifier Decomposition
Heming Xia, Peiyi Wang, Tianyu Liu +3
Continual relation extraction (CRE) models aim at handling emerging new relations while avoiding catastrophically forgetting old ones in the streaming data. Though improvements hav…
Large Language Models are not Fair Evaluators
Peiyi Wang, Lei Li, Liang Chen +7
In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e.g., GPT-4, as a referee to score and compare the quality of respo…