Papers by Hal Daumé Iii
SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Toxic content encompasses a wide spectrum of terminologies whose definitions vary by platform. |
| Approach: | They propose a 2-stage framework for explainable content moderation using Large Language Models (LLMs) they leverage LLMs’ own outputs to generate synthetic explanations for correct and incorrect labels . they refine explanation quality through cross-model training, allowing weaker models to align with stronger ones. |
| Outcome: | Experiments on 3 benchmarks show that the proposed framework achieves 13% macro-F1 improvement over few-shot baselines using only 6-57% of training data. |
Toxicity Detection is NOT all you Need: Measuring the Gaps to Supporting Volunteer Content Moderators through a User-Centric Method (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing efforts to automate content moderation have focused on identifying toxic, offensive, and hateful content . yet, it remains unclear whether improvements have addressed the needs of volunteer content moderators . |
| Approach: | They propose to use a model review to examine the availability of moderators' models to flag violations of various forum rules. |
| Outcome: | The proposed models perform poorly on a significant portion of the rules. |
Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style (2026.acl-long)
Copied to clipboard
| Challenge: | Despite the growing use of large language models for writing tasks, it remains unclear whether users can effectively reshape LLM-generated text to reflect their personal style. |
| Approach: | They conduct an online study in which participants post-edit LLM-generated drafts for writing tasks where personal style matters to them. |
| Outcome: | The results show that post-editing increases stylistic similarity to unassisted writing and reduces similarity with fully LLM-generated output. |
HateCOT: An Explanation-Enhanced Dataset for Generalizable Offensive Speech Detection via Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Social media has amplified the propagation of hateful sentiments, highlighting the contested nature of "offensive content" research shows that "of offensive content" is still a contested construct due to varying definitions and labeling. |
| Approach: | They propose a dataset that features human-curated explanations for offensive content in English . they show that HateCOT pretraining improves performance of open-source LLMs . |
| Outcome: | The proposed model improves on three benchmark datasets for offensive content detection . the model improve the quality of its explanations, as confirmed by the human evaluation . |
Reheat Nachos for Dinner? Evaluating AI Support for Cross-Cultural Communication of Neologisms (2026.findings-acl)
Copied to clipboard
| Challenge: | Neologisms and emerging slang are central to daily conversation, yet challenging for non-native speakers (NNS) to interpret and use appropriately in cross-cultural communication with native speakers (NS). |
| Approach: | They use AI to learn English neologisms and write messages using the learned word to an NS friend. |
| Outcome: | The proposed model shows that AI Explanation yields the largest gains over no support in NS-rated competence, while contextual appropriateness judgments show indifference across support. |
ASL STEM Wiki: Dataset and Benchmark for Interpreting STEM Articles (2024.emnlp-main)
Copied to clipboard
Kayo Yin, Chinmay Singh, Fyodor Minakov, Vanessa Milan, Hal Daumé Iii, Cyril Zhang, Alex Lu, Danielle Bragg
| Challenge: | Deaf and hard-of-hearing students face significant barriers in accessing STEM education due to the scarcity of STEM resources in signed languages. |
| Approach: | They develop models to identify fingerspelled words in American Sign Language (ASL) given an English sentence and a video, the model detects which English phrase is fingerspelled in the clip. |
| Outcome: | ASL STEM Wiki is the first continuous signing dataset focused on STEM . it detects fingerspelled words and queries them for appropriate signs to suggest to interpreters. |
Do great minds think alike? Investigating Human-AI Complementarity in Question Answering with CAIMIRA (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models have led to claims of AI surpassing humans in QA tasks . authors: models are purportedly acing tests that many humans find challenging . |
| Approach: | They propose a framework that enables quantitative assessment and comparison of problem-solving abilities in QA agents. |
| Outcome: | The proposed framework uncovers distinctficiency patterns in knowledge domains and reasoning skills. |
“You Gotta be a Doctor, Lin” : An Investigation of Name-Based Bias of Large Language Models in Employment Recommendations (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated racial and gender biases in various applications. |
| Approach: | They use Large Language Models to simulate hiring decisions and salary recommendations for candidates with 320 first names that strongly signal their race and gender, across over 750,000 prompts. |
| Outcome: | The proposed models favor candidates with White female-sounding names over other demographic groups across 40 occupations. |
Large Language Models Help Humans Verify Truthfulness – Except When They Are Convincingly Wrong (2024.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used for accessing information on the web. |
| Approach: | They conduct experiments with 80 crowdworkers to compare LLMs with search engines . they ask LLM to provide contrastive information to reduce over-reliance on LLM . |
| Outcome: | The results show that LLMs can outperform search engines but not LLM explanations . the study shows that LMS explanations are not reliable replacements for reading retrieved passages compared to search engines alone. |
Understanding the Impacts of Language Technologies’ Performance Disparities on African American Language Speakers (2024.findings-acl)
Copied to clipboard
| Challenge: | Previous work has examined performance disparities between AAL speakers and White Mainstream English speakers . but, this work has not sought to understand the impacts of these disparities on AAL speaker. |
| Approach: | They examine the experiences of African American Language (AAL) speakers when using language technologies. |
| Outcome: | The authors interview 19 AAL speakers to understand performance disparities . they find that speakers often undertake invisible labor to successfully use language technologies . |
Successfully Guiding Humans with Imperfect Instructions by Highlighting Potential Errors and Suggesting Corrections (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems that only provide instructions generate inaccurate instructions . however, language models can still guide humans toward making sound decisions . |
| Approach: | They develop a system that can detect and correct errors in natural language instructions . it can also be used to narrow down search space and reduce misguidance . |
| Outcome: | The proposed system achieves a 13% increase in success rate and a 29% reduction in final location error distance with 80 users. |