4 papers · 1 filter
RegExtract: A Benchmark for PFAS Regulatory Information Extraction with LLMs
Defne Circi, Krystelle Lionti, Sarathkrishna Swaminathan +8
Extracting structured information from regulatory documents is a critical but challenging task. Relevant facts are scattered across long, legally dense texts, and traceability of e…
Adaptive Decoding via Test-Time Policy Learning for Self-Improving Generation
Asmita Bhardwaj, Yuya Jeremy Ong, Eelaaf Zahid +1
Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static an…
Evaluating Ill-Defined Tasks in Large Language Models
Yi Zhou, Basel Shbita
Many evaluations of Large Language Models (LLMs) target tasks that are inherently ill-defined, with unclear input and output spaces and ambiguous success criteria. We analyze why e…
Viola: A Topic Agnostic Generate-and-Rank Dialogue System
Hyundong Cho, Basel Shbita, Kartik Shenoy +5
We present Viola, an open-domain dialogue system for spoken conversation that uses a topic-agnostic dialogue manager based on a simple generate-and-rank approach. Leveraging recent…