8 papers
Reproducible Synthetic Clinical Letters for Seizure Frequency Information Extraction
Yujian Gan, Stephen H. Barlow, Ben Holgate +4
Seizure-frequency information is important for epilepsy research and clinical care, but it is usually recorded in variable free-text clinic letters that are hard to annotate and sh…
Fine-Refine: Iterative Fine-grained Refinement for Mitigating Dialogue Hallucination
Xiangyan Chen, Yujian Gan, Matthew Purver
The tendency for hallucination in current large language models (LLMs) negatively impacts dialogue systems. Such hallucinations produce factually incorrect responses that may misle…
Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension
Juexi Shao, Siyou Li, Yujian Gan +3
Dialogue-Based Generalized Referring Expression Comprehension (GREC) requires models to ground the expression and unlimited targets in complex visual scenes while resolving corefer…
Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models
Siyou Li, Huanan Wu, Juexi Shao +10
Despite the recent advances in the video understanding ability of multimodal large language models (MLLMs), long video understanding remains a challenge. One of the main issues is…
Improving LLMs' Learning for Coreference Resolution
Yujian Gan, Yuan Liang, Yanni Lin +2
Coreference Resolution (CR) is crucial for many NLP tasks, but existing LLMs struggle with hallucination and under-performance. In this paper, we investigate the limitations of exi…
FineDialFact: A benchmark for Fine-grained Dialogue Fact Verification
Xiangyan Chen, Yufeng Li, Yujian Gan +2
Large language models are known to produce hallucinations - factually incorrect or fabricated information - which poses significant challenges for many natural language processing…
Improving Factuality for Dialogue Response Generation via Graph-Based Knowledge Augmentation
Xiangyan Chen, Yujian Gan, Yimeng Gu +1
Large Language Models (LLMs) succeed in many natural language processing tasks. However, their tendency to hallucinate - generate plausible but inconsistent or factually incorrect…
ClarQ-LLM: A Benchmark for Models Clarifying and Requesting Information in Task-Oriented Dialog
Yujian Gan, Changling Li, Jinxia Xie +3
We introduce ClarQ-LLM, an evaluation framework consisting of bilingual English-Chinese conversation tasks, conversational agents and evaluation metrics, designed to serve as a str…