2 citations · 8 across the 14 of their papers we have counts for
8 papers · 1 filter
Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents
Ying He, Zhouhong Gu, Zhecheng Hu +8
Ensuring the accuracy of financial documents is critical for economic analysis, regulatory compliance, and corporate decision-making. Several studies have shown that Large Language…
Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models
Yuyan Chen, Qiang Fu, Yichen Yuan +6
Large Language Models (LLMs) have gained widespread adoption in various natural language processing tasks, including question answering and dialogue systems. However, a major drawb…
MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization
Yuyan Chen, Zhihao Wen, Ge Fan +6
Prompt engineering, as an efficient and effective way to leverage Large Language Models (LLM), has drawn a lot of attention from the research community. The existing research prima…
ESC-Eval: Evaluating Emotion Support Conversations in Large Language Models
Haiquan Zhao, Lingyu Li, Shisong Chen +11
Emotion Support Conversation (ESC) is a crucial application, which aims to reduce human stress, offer emotional guidance, and ultimately enhance human mental and physical well-bein…
AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation
Wenhao Huang, Zhouhong Gu, Chenghao Peng +5
Web scraping is a powerful technique that extracts data from websites, enabling automated data collection, enhancing data analysis capabilities, and minimizing manual data entry ef…
Is There a One-Model-Fits-All Approach to Information Extraction? Revisiting Task Definition Biases
Wenhao Huang, Qianyu He, Zhixu Li +2
Definition bias is a negative phenomenon that can mislead models. Definition bias in information extraction appears not only across datasets from different domains but also within…
OVEL: Large Language Model as Memory Manager for Online Video Entity Linking
Haiquan Zhao, Xuwu Wang, Shisong Chen +3
In recent years, multi-modal entity linking (MEL) has garnered increasing attention in the research community due to its significance in numerous multi-modal applications. Video, a…
Source Prompt: Coordinated Pre-training of Language Models on Diverse Corpora from Multiple Sources
Yipei Xu, Dakuan Lu, Jiaqing Liang +7
Pre-trained language models (PLMs) have established the new paradigm in the field of NLP. For more powerful PLMs, one of the most popular and successful way is to continuously scal…