From the 1 of 27 linked papers with an AI index.
27 papers
Answer-Conditioned Chains of Thought Degrade Verifiable-Reasoning Distillation in Large Language Models
Jungseob Lee, Seungyoon Lee, Suhyune Son +4
The paper shows that conditioning large language models on the correct answer when generating chains of thought harms the quality of distilled reasoning data, leading to large drop…
NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models
Hyeonseok Moon, Heuiseok Lim
Recent reports suggest that LLMs can handle increasingly long contexts. However, many existing benchmarks for context understanding embed substantial query-irrelevant content, whic…
Unveiling the Limits of Large Language Models in Inferring Pragmatic Meaning from Non-Verbal Responses
Sugyeong Eo, Heuiseok Lim
Although large language models (LLMs) have shown considerable progress in pragmatic language understanding, prior research has focused mainly on their comprehension of verbal behav…
No Reader Left Behind: Multi-Agent Summaries Everyone Can Understand
Jimin Jung, MyoungJin Kim, Jaehyung Seo +1
The Plain Writing Act in the United States requires government documents to be accessible in clear and simple language that the general public can easily understand, yet existing s…
HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering
Joongmin Shin, Gyuho Shim, Jeongbae Park +2
Retrieval-augmented generation (RAG) for document-based Open-domain Question Answering (ODQA) on large-scale industrial corpora faces two critical bottlenecks: routing failure in l…
Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging
Youngjoon Jang, Junyoung Son, Taemin Lee +5
With the increasing utilization of multilingual text information, Cross-Lingual Information Retrieval (CLIR) has become a crucial research area. However, the impact of training dat…