no code implementations • 5 Apr 2024 • Diyi Yang, Caleb Ziems, William Held, Omar Shaikh, Michael S. Bernstein, John Mitchell
People rely on social skills like conflict resolution to communicate effectively and to thrive in both work and personal life.
no code implementations • 22 Feb 2024 • Michael J. Ryan, William Held, Diyi Yang
Before being deployed for user-facing applications, developers align Large Language Models (LLMs) to user preferences through a variety of procedures, such as Reinforcement Learning From Human Feedback (RLHF) and Direct Preference Optimization (DPO).
no code implementations • 14 Nov 2023 • William Held, Camille Harris, Michael Best, Diyi Yang
Coloniality, the continuation of colonial harms beyond "official" colonization, has pervasive effects across society and scientific fields.
1 code implementation • 2 Nov 2023 • Zedian Xiao, William Held, Yanchen Liu, Diyi Yang
Large Language Models (LLMs) are trained on corpora disproportionally weighted in favor of Standard American English.
1 code implementation • 4 Jun 2023 • Omar Shaikh, Caleb Ziems, William Held, Aryan J. Pariani, Fred Morstatter, Diyi Yang
Prior work uses simple reference games to test models of pragmatic reasoning, often with unidentified speakers and listeners.
1 code implementation • 22 May 2023 • Yanchen Liu, William Held, Diyi Yang
We show that DADA is effective for both single task and instruction finetuned language models, offering an extensible and interpretable framework for adapting existing LLMs to different English dialects.
1 code implementation • 12 Apr 2023 • Caleb Ziems, William Held, Omar Shaikh, Jiaao Chen, Zhehao Zhang, Diyi Yang
We conclude that the performance of today's LLMs can augment the CSS research pipeline in two ways: (1) serving as zero-shot data annotators on human annotation teams, and (2) bootstrapping challenging creative generation tasks (e. g., explaining the underlying attributes of a text).
no code implementations • 15 Dec 2022 • Caleb Ziems, William Held, Jingfeng Yang, Jwala Dhamala, Rahul Gupta, Diyi Yang
First, we use this system to stress tests question answering, machine translation, and semantic parsing.
1 code implementation • 15 Dec 2022 • William Held, Christopher Hidey, Fei Liu, Eric Zhu, Rahul Goel, Diyi Yang, Rushin Shah
Modern virtual assistants use internal semantic parsing engines to convert user utterances to actionable commands.
1 code implementation • 15 Dec 2022 • Omar Shaikh, Hongxin Zhang, William Held, Michael Bernstein, Diyi Yang
Generating a Chain of Thought (CoT) has been shown to consistently improve large language model (LLM) performance on a wide range of NLP tasks.
no code implementations • 11 Oct 2022 • William Held, Diyi Yang
However, as a fixed-size model acquires more languages, its performance across all languages degrades, a phenomenon termed interference.
1 code implementation • EMNLP 2021 • William Held, Dan Iter, Dan Jurafsky
We model the entities/events in a reader's focus as a neighborhood within a learned latent embedding space which minimizes the distance between mentions and the centroids of their gold coreference clusters.
Ranked #1 on Event Coreference Resolution on Gun Violence Corpus
coreference-resolution Entity Cross-Document Coreference Resolution +2
no code implementations • ACL 2019 • William Held, Nizar Habash
Hypernymy modeling has largely been separated according to two paradigms, pattern-based methods and distributional methods.