117 citations · 150 across the 36 of their papers we have counts for
10 papers · 1 filter
P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
Shuai Zhao, Xinyi Wu, Shiqian Zhao +4
During fine-tuning, large language models (LLMs) are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, ex…
Unsupervised Hallucination Detection by Inspecting Reasoning Processes
Ponhvoan Srey, Xiaobao Wu, Anh Tuan Luu
Unsupervised hallucination detection aims to identify hallucinated content generated by large language models (LLMs) without relying on labeled data. While unsupervised methods hav…
Affective-ROPTester: Capability and Bias Analysis of LLMs in Predicting Retinopathy of Prematurity
Shuai Zhao, Yulin Zhang, Luwei Xiao +7
Despite the remarkable progress of large language models (LLMs) across various domains, their capacity to predict retinopathy of prematurity (ROP) risk remains largely unexplored.…
Read as You See: Guiding Unimodal LLMs for Low-Resource Explainable Harmful Meme Detection
Fengjun Pan, Xiaobao Wu, Tho Quan +1
Detecting harmful memes is crucial for safeguarding the integrity and harmony of online environments, yet existing detection methods are often resource-intensive, inflexible, and l…
SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation
Huimin Xu, Xin Mao, Feng-Lin Li +4
Process Reward Models (PRMs) have demonstrated promising results in mathematical reasoning, but existing process annotation approaches, whether through human annotations or Monte C…
Aspect-Based Summarization with Self-Aspect Retrieval Enhanced Generation
Yichao Feng, Shuai Zhao, Yueqiu Li +3
Aspect-based summarization aims to generate summaries tailored to specific aspects, addressing the resource constraints and limited generalizability of traditional summarization ap…
CodeArena: A Collective Evaluation Platform for LLM Code Generation
Mingzhe Du, Anh Tuan Luu, Bin Ji +5
Large Language Models (LLMs) have reshaped code generation by synergizing their exceptional comprehension of natural language and programming syntax, thereby substantially boosting…
Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
Huimin Xu, Xin Mao, Feng-Lin Li +4
Direct Preference Optimization (DPO) often struggles with long-chain mathematical reasoning. Existing approaches, such as Step-DPO, typically improve this by focusing on the first…
CutPaste&Find: Efficient Multimodal Hallucination Detector with Visual-aid Knowledge Base
Cong-Duy Nguyen, Xiaobao Wu, Duc Anh Vu +3
Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal reasoning capabilities, but they remain susceptible to hallucination, particularly object hallucination…
Enhancing Multimodal Entity Linking with Jaccard Distance-based Conditional Contrastive Learning and Contextual Visual Augmentation
Cong-Duy Nguyen, Xiaobao Wu, Thong Nguyen +5
Previous research on multimodal entity linking (MEL) has primarily employed contrastive learning as the primary objective. However, using the rest of the batch as negative samples…