9 papers
CompLit: Scientific Literature Search Benchmarks Must Cover Implicit, Cumulative, and Unmet Needs
Dayoon Ko, Jihyuk Kim, Soyeong Jeong +6
How much can we trust an agent to find the paper we need? As researchers, we search the literature from what we have read toward what we have not. We thus describe what we want in…
When Is Enough Not Enough? Illusory Completion in Search Agents
Dayoon Ko, Jihyuk Kim, Sohyeon Kim +5
In agentic search, an LLM agent searches the web, reads the pages it finds, and decides what to look for next before returning an answer. But can we trust an answer simply because…
Zero2Text: Zero-Training Cross-Domain Inversion Attacks on Textual Embeddings
Doohyun Kim, Donghwa Kang, Kyungjae Lee +2
The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via embedding inversi…
Assessing LLM Reasoning Steps via Principal Knowledge Grounding
Hyeon Hwang, Yewon Cho, Chanwoong Yoon +5
Step-by-step reasoning has become a standard approach for large language models (LLMs) to tackle complex tasks. While this paradigm has proven effective, it raises a fundamental qu…
Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection
Taeheon Lim, Joohyung Lee, Kyungjae Lee +1
The Federated Learning (FL) approach enables effective learning across distributed systems, while preserving user data privacy. To date, research has primarily focused on addressin…
One Missing Piece for Open-Source Reasoning Models: A Dataset to Mitigate Cold-Starting Short CoT LLMs in RL
Hyungjoo Chae, Dongjin Kang, Jihyuk Kim +6
With the release of R1, a publicly available large reasoning model (LRM), researchers commonly train new LRMs by training language models on R1's long chain-of-thought (CoT) infere…
Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation
Takyoung Kim, Kyungjae Lee, Young Rok Jang +4
Interactions with large language models (LLMs) often yield long and detailed responses, leveraging both parametric knowledge and retrieval-augmented generation (RAG). While these r…
KU-DMIS at EHRSQL 2024:Generating SQL query via question templatization in EHR
Hajung Kim, Chanhwi Kim, Hoonick Lee +5
Transforming natural language questions into SQL queries is crucial for precise data retrieval from electronic health record (EHR) databases. A significant challenge in this proces…
PreWoMe: Exploiting Presuppositions as Working Memory for Long Form Question Answering
Wookje Han, Jinsol Park, Kyungjae Lee
Information-seeking questions in long-form question answering (LFQA) often prove misleading due to ambiguity or false presupposition in the question. While many existing approaches…