2 papers
cs.IR2026
Checking Fact with Better Retrieval: Dynamic Contrastive Learning for Evidence Retrieval
Zhongtian Hua, Yi Luo, Meijia Yu +1
In the field of multimodal fact checking, the accuracy of retrieving evidence from different modalities has a significant impact on the downstream claim verification process. Exist…
cs.CL2025
JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Sampling
Jinwang Song, Hongying Zan, Kunli Zhang +4
Text-to-SQL, which maps natural language to SQL queries, has benefited greatly from recent advances in Large Language Models (LLMs). While LLMs offer various paradigms for this tas…