Papers by Daniel McDuff

5 papers
NICE: Neural Image Commenting with Empathy (2021.findings-emnlp)

Copied to clipboard

Challenge: Emotion and empathy are examples of human qualities lacking in many human-machine interactions.
Approach: They propose to generate images with human-generated comments with enhanced emotion and empathy while minimizing inappropriate or offensive outputs.
Outcome: The proposed model generates more human-like and engaging image comments on two images with human-generated comments and human annotations while minimizing inappropriate or offensive outputs.
Substance over Style: Evaluating Proactive Conversational Coaching Agents (2025.acl-long)

Copied to clipboard

Challenge: Recent NLP research has focused on single-turn tasks with well-defined objectives or evaluation criteria.
Approach: They describe five multi-turn coaching agents that exhibit distinct conversational styles and evaluate them through a user study.
Outcome: The authors compare user feedback with third-person evaluations from health experts and an LM to find that stylistic components in absence of core functionality are viewed negatively.
Logical Transformers: Infusing Logical Structures into Pre-Trained Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Existing pre-trained language models that ignore the logical structures underlying natural language text often lack the ability to capture and encode key logical information in the input sequences.
Approach: They propose to construct logic-aware input embeddings for transformer language models through logic detection, logic mapping and hierarchical logical projections and then develop a new modeling paradigm that can upgrade existing transformer language model into logical transformers to boost their performance.
Outcome: The proposed model can achieve superior performance on four important and challenging tasks.
BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) struggle with proactive engagement, authors say . a blind clinical evaluation confirmed that trained agents exhibit more realistic clinical behavior .
Approach: They propose a training strategy using behavioral tokens to explicitly condition LLMs for dynamic behavioral selection.
Outcome: The proposed training strategy boosts performance on both benchmarks.
What Are the Odds? Language Models Are Capable of Probabilistic Reasoning (2024.emnlp-main)

Copied to clipboard

Challenge: Language models (LMs) are capable of remarkably complex linguistic tasks, but numerical reasoning is an area in which they struggle.
Approach: They evaluate the probabilistic reasoning capabilities of language models using idealized and real-world statistical distributions.
Outcome: The proposed model can make inferences about distributions, even if assumptions are incorrect or misspecified.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations