activity
20212023
most citedDialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues

19 citations · 115 across the 24 of their papers we have counts for

collaborators
Showing cs.CLShow all

26 papers · 1 filter

cs.CL2023★ 1 cited

Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions

Sachin Kumar, Chan Young Park, Yulia Tsvetkov

Language model (LM) prompting--a popular paradigm for solving NLP tasks--has been shown to be susceptible to miscalibration and brittleness to slight prompt variations, caused by i…

cs.CL2023

P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models

Yuhan Liu, Shangbin Feng, Xiaochuang Han +4

In this work, we take a first step towards designing summarization systems that are faithful to the author's intent, not only the semantic content of the article. Focusing on a cas…

cs.CL2023★ 1 cited

Understanding In-Context Learning via Supportive Pretraining Data

Xiaochuang Han, Daniel Simig, Todor Mihaylov +3

In-context learning (ICL) improves language models' performance on a variety of NLP tasks by simply demonstrating a handful of examples at inference time. It is not well understood…

cs.CL2023

Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Tracker

Melanie Sclar, Sachin Kumar, Peter West +3

Theory of Mind (ToM)$\unicode{x2014}$the ability to reason about the mental states of other people$\unicode{x2014}$is a key element of our social intelligence. Yet, despite their e…

cs.CL2023★ 16 cited

Examining risks of racial biases in NLP tools for child protective services

Anjalie Field, Amanda Coston, Nupoor Gandhi +4

Although much literature has established the presence of demographic bias in natural language processing (NLP) models, most work relies on curated bias metrics that may not be refl…

cs.CL2023★ 8 cited

BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer

Akari Asai, Sneha Kudugunta, Xinyan Velocity Yu +6

Despite remarkable advancements in few-shot generalization in natural language processing, most models are developed and evaluated primarily in English. To facilitate research on f…