9 papers
Don't Scroll Back: Missing-Evidence Memory for Streaming Dialogue Summarization
Hyangsuk Min, Hwanjun Song
Users of modern platforms repeatedly need summaries of recent dialogue, but the window rarely contains enough context to be interpreted on its own. We formalize this setting as str…
Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability
Jeonghwan Choi, Taewon Yun, Minjeong Ban +3
Retrieval-augmented generation improves the factuality of large language models by grounding responses in retrieved evidence, yet existing evaluation frameworks struggle to provide…
Solar Open 2 Technical Report
Sungrae Park, Sanghoon Kim, Gyoungjin Gim +50
We present Solar Open 2, a 250B-A15B Mixture-of-Experts language model built for long-horizon agentic tasks, scaled up from Solar Open 1 (Solar Open 100B). To hold entire agent tra…
SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations
Taewon Yun, Hyeonseong Park, Jeonghwan Choi +3
Evaluating LLM mediators remains challenging, as mediation unfolds as a real-time trajectory shaped by disputants' shifting emotions, intentions, and context. Existing testbeds rel…
Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding
Taewon Yun, Jisu Shin, Jeonghwan Choi +2
Distilling large reasoning models is essential for making Long-CoT reasoning practical, as full-scale inference remains computationally prohibitive. Existing curation-based approac…
What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents
Jeonghwan Choi, Jibin Hwang, Gyeonghun Sun +4
Evaluating retail strategies before deployment is difficult, as outcomes are determined across multiple stages, from seller-side persuasion through buyer-seller interaction to purc…