12 papers
Be Consistent! Enhancing Robust Visual Reasoning in LVLMs with Consistency Constraints
Liqiang Jing, Xiong Zhou, Siddharth Varia +3
While Large Vision-Language Models (LVLMs) exhibit strong perceptual capabilities, they remain vulnerable in visual reasoning tasks. Existing benchmarks largely focus on symbolic m…
When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors
Yuqing Yang, Qi Zhu, Zhen Han +5
While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understan…
Scalable Prompt Routing via Fine-Grained Latent Task Discovery
Yunyi Zhang, Soji Adeshina, Sheng Guan +5
Prompt routing dynamically selects the most appropriate large language model from a pool of candidates for each query, optimizing performance while managing costs. As model pools s…
The Kinetics of Reasoning: How Chain-of-Thought Shapes Learning in Transformers?
Zihan Pengmei, Costas Mavromatis, Zhengyuan Shen +3
Chain-of-thought (CoT) supervision can substantially improve transformer performance, yet the mechanisms by which models learn to follow and benefit from CoT remain poorly understo…
GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models
Jialin Chen, Houyu Zhang, Seongjun Yun +6
Retrieval-Augmented Generation (RAG) has significantly mitigated the hallucinations of Large Language Models (LLMs) by grounding the generation with external knowledge. Recent exte…
BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering
Costas Mavromatis, Soji Adeshina, Vassilis N. Ioannidis +6
Knowledge graph question answering (KGQA) presents significant challenges due to the structural and semantic variations across input graphs. Existing works rely on Large Language M…