Papers by Hal Daumé Iii
Investigating Dictionary Expansion for Video-based Sign Language Dictionaries (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, most dictionary retrieval methods only work with fixed vocabularies, and it is unclear how they might support dictionary expansion without retraining. |
| Approach: | They propose to use a representation-based method to explore the feasibility of dictionary expansion for sign language dictionaries. |
| Outcome: | The proposed method improves sign language dictionaries by varying number of signs added and amount of data for newly added signs. |
Language Models Predict Empathy Gaps Between Social In-groups and Out-groups (2025.naacl-long)
Copied to clipboard
| Challenge: | Studies of human psychology have shown that people are more motivated to extend empathy to in-group members than out-group member. |
| Approach: | They propose to use language models to study intergroup empathy gap . they use a short description of an experience to predict emotion intensity . |
| Outcome: | The proposed model exhibited strongest intergroup bias among those tested. |
My LLM might Mimic AAE - But When Should It? (2025.naacl-long)
Copied to clipboard
| Challenge: | a study examines the representation of African American English in large language models . a survey of black americans and annotation of LLM outputs shows that Black Americans prefer to use AAE in formal settings . |
| Approach: | They examine Black Americans' perceptions of how effective AI tools are at producing authentic African American English in large language models. |
| Outcome: | The results show that Black Americans prefer to use LLMs in formal settings over informal ones . the results show they prefer to produce AAE in less formal settings . |
Can Hallucination Correction Improve Video-Language Alignment? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing work on hallucination correction for large vision-language models focuses on mitigating hallucisations, but a new approach is needed to improve video-language alignment. |
| Approach: | They propose a self-training framework learning to correct hallucinations in descriptions that do not align with the video content. |
| Outcome: | The proposed framework improves video-language alignment by identifying and correcting inconsistencies in descriptions that do not align with the video content. |
A Necessary Step toward Faithfulness: Measuring and Improving Consistency in Free-Text Explanations (2025.emnlp-main)
Copied to clipboard
| Challenge: | a measure of faithful free-text explanations is difficult to generate by language models and assess by humans. |
| Approach: | They propose a measure of Prediction-EXplanation consistency by extending the concept of weight of evidence. |
| Outcome: | The proposed measure improves explanation faithfulness by up to 9.7%, the authors show . they show that applying preference optimization improves the consistency of generated explanations across three model families. |
‘Rich Dad, Poor Lad’: How do Large Language Models Contextualize Socioeconomic Factors in College Admission ? (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models are increasingly involved in high-stakes domains, yet how they reason about socially sensitive decisions remains underexplored. |
| Approach: | They propose a dual-process audit framework to probe LLMs’ reasoning behaviors in sensitive applications using a synthetic dataset of 30,000 applicant profiles grounded in real-world correlations. |
| Outcome: | The proposed framework exploits a synthetic dataset of 30,000 applicant profiles grounded in real-world correlations to probe LLMs' reasoning behaviors in sensitive applications. |
An Interdisciplinary Approach to Human-Centered Machine Translation (2025.emnlp-main)
Copied to clipboard
Marine Carpuat, Omri Asscher, Kalika Bali, Luisa Bentivogli, Fred Blain, Lynne Bowker, Monojit Choudhury, Hal Daumé Iii, Kevin Duh, Ge Gao, Alvin C Grissom II, Marzena Karpinska, Elaine C Khoong, William D. Lewis, Andre Martins, Mary Nurminen, Douglas W. Oard, Maja Popovic, Michel Simard, François Yvon
| Challenge: | Despite progress in MT, a gap persists between how the technology is developed and how it is used in real-world contexts. |
| Approach: | They propose a human-centered approach to machine translation (MT) they argue that MT should be evaluated with diverse goals and contexts of use . |
| Outcome: | The proposed approach emphasizes alignment of evaluation and design with diverse communicative goals and contexts of use. |
Who’s the Author? How Explanations Impact User Reliance in AI-Assisted Authorship Attribution (2025.findings-emnlp)
Copied to clipboard
| Challenge: | despite growing interest in explainable NLP, it remains unclear how explanation strategies shape user behavior in tasks like authorship identification. |
| Approach: | They propose two explanation types to support their analysis of user behavior . they use example-based style rewrites and feature-based rationales to generate explanations . |
| Outcome: | The proposed explanations support appropriate reliance, whereas explanations increase AI overreliance, the study finds . |