Search Results for author: Jordan Lee Boyd-Graber

Found 8 papers, 5 papers with code

Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas

1 code implementation20 Jan 2025 Nishant Balepur, Vishakh Padmakumar, Fumeng Yang, Shi Feng, Rachel Rudinger, Jordan Lee Boyd-Graber

However, this preference data format does not convey why users prefer responses that are chosen or rejected, so LLMs trained on these datasets cannot tailor responses to varied user needs.

Personalized Help for Optimizing Low-Skilled Users' Strategy

no code implementations14 Nov 2024 Feng Gu, Wichayaporn Wongkamjan, Jordan Lee Boyd-Graber, Jonathan K. Kummerfeld, Denis Peskoff, Jonathan May

AIs can beat humans in game environments; however, how helpful those agents are to human remains understudied.

PEDANTS: Cheap but Effective and Interpretable Answer Equivalence

1 code implementation17 Feb 2024 Zongxia Li, Ishani Mondal, Yijun Liang, Huy Nghiem, Jordan Lee Boyd-Graber

Question answering (QA) can only make progress if we know if an answer is correct, but current answer correctness (AC) metrics struggle with verbose, free-form answers from large language models (LLMs).

Benchmarking Open-Domain Question Answering +1

Is Automated Topic Model Evaluation Broken? The Incoherence of Coherence

1 code implementation NeurIPS 2021 Alexander Hoyle, Pranav Goel, Andrew Hian-Cheong, Denis Peskov, Jordan Lee Boyd-Graber, Philip Resnik

To address the standardization gap, we systematically evaluate a dominant classical model and two state-of-the-art neural models on two commonly used datasets.

Topic Models

Cannot find the paper you are looking for? You can Submit a new open access paper.