7 accepted papers
Recent studies have raised significant concerns regarding the reliability of current mathematical benchmarks, highlighting key limitations such as simplistic design and potential data contamination that undermine evaluation accuracy. Consequently, developing a reliable benchmark that effectively eva
In collaborative filtering, learning effective embeddings for users and items from interaction data remains a central challenge. While recent efforts leverage large language models (LLMs) to enhance collaborative filtering, two critical limitations persist: (1) Efficiency: LLM-based inference is sig
Recent advancements in large language models (LLMs) have shown promise in bridging the gap between natural language queries and database management systems, enabling users to interact with databases without the background of SQL. However, LLMs often struggle to fully exploit and comprehend the user…
Modeling text-attributed graphs is a well-known problem due to the difficulty of capturing both the text attribute and the graph structure effectively. Existing models often focus on either the text attribute or the graph structure, potentially neglecting the other aspect. This is primarily because…
Current fact verification methods generally follow the two-stage training paradigm: evidence retrieval and claim verification. While existing works focus on developing sophisticated claim verification modules, the fundamental importance of evidence retrieval is largely ignored. Existing approaches u…
Generating accurate SQL queries for user questions (text-to-SQL) has been a long-standing challenge since it requires a deep understanding of both the user’s question and the corresponding database schema in order to retrieve the desired content accurately. Existing methods rely on the comprehensive…
Nowadays, detecting multimodal fake news has emerged as a foremost concern since the widespread dissemination of fake news may incur adverse societal impact. Conventional methods generally focus on capturing the linguistic and visual semantics within the multimodal content, which fall short in effe…