2024年7月18日 · View a PDF of the paper titled Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction, by Suma Bailis and 2 other authors View PDF HTML (experimental) Abstract: This paper introduces Werewolf Arena, a novel framework for evaluating large language models (LLMs) through the lens of the classic social deduction game, Werewolf.

Semantic Scholar profile for Suma Bailis, with 2 highly influential citations and 3 scientific research papers.

5 天之前 · AI researchers have posited Dungeons and Dragons (D&D) as a challenge problem to test systems on various language-related capabilities. In this paper, we frame D&D specifically as a dialogue system challenge, where the tasks are to both generate the next conversational turn in the game and predict the state of the game given the dialogue history.

Poster in Workshop: Generative AI for Education (GAIED): Advances, Opportunities, and Challenges Paper 33: WordPlay: An Agent Framework for AuthoringPlayful Language Learning Puzzles Suma Bailis · Lara McConnaughey · Jane Friedhoff · Feiyang Chen · Chase Adams · Jacob Moon · Lara McConnaughey

Human language reveals a universal positivity bias. JR Williams, PR Lessard, S Desu, EM Clark, JP Bagrow, CM Danforth, ...

Chris Callison-Burch | Gaurav Singh Tomar | Lara J. Martin | Daphne Ippolito | Suma Bailis | David Reitter Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing AI researchers have posited Dungeons and Dragons (D&D) as a challenge problem to test systems on various language-related capabilities.

Suma Bailis has worked with google, apple, massachusetts institute of technology

-- · Location: 94110. View Suma Bailis’ profile on LinkedIn, a professional community of 1 billion members.

AI researchers have posited Dungeons and Dragons (D&D) as a challenge problem to test systems on various language-related capabilities. In this paper, we frame D&D specifically as a dialogue system challenge, where the tasks are to both generate the next conversational turn in the game and predict the state of the game given the dialogue history.