7 citations · 22 across the 15 of their papers we have counts for
19 papers
Verb-ICL: Rethinking In-Context Learning for Structured Prediction
Fan Bai, Hengshuo Miao, Sanjit S Batra +3
Structured prediction tasks pose unique challenges for in-context learning (ICL): their compositional outputs require modeling fine-grained, token-level patterns that sentence-leve…
PrimeScientist: Strategic Allocation of Research Effort in Autonomous Research
Xinle Yu, Fan Bai, Kaiser Sun +5
Autonomous research agents aim to automate scientific workflows, from proposing ideas to conducting experiments and analyzing results. Yet current AI and research agents can propos…
Not Another Text Benchmark: Putting the "Visual" Back in Visual Question Answering for Large Video Models
Rwiddhi Chakraborty, Yinong, Yinong Oliver Wang +9
Large video models have exhibited impressive performance on a wide range of visual question answering tasks, owing to the rise of powerful, pretrained text and vision encoders. The…
Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States
Zixuan Wang, Yufan Zhou, Jinzhou Tang +16
As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the people they serve. Yet training…
Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining
Michael K. Chen, Xikun Zhang, Fan Bai +2
As AI labs approach a data ceiling where compute capacity outpaces the rate of new high-quality text generation, language model pretraining is shifting toward a data-constrained, c…
Agent-as-Peer-Debriefer: A Multi-Agent Framework with Perspective-Based Refinement for Qualitative Analysis
Zhimin Lin, Kun Cheng, Zhiyao Shu +4
Large language models (LLMs) are increasingly used for qualitative data analysis (QDA), yet their outputs often miss the depth and nuance of human analysis. We argue this gap refle…
Reading, Not Thinking: Understanding and Bridging the Modality Gap When Text Becomes Pixels in Multimodal LLMs
Kaiser Sun, Xiaochuang Yuan, Hongjun Liu +4
Multimodal large language models (MLLMs) can process text presented as images, yet they often perform worse than when the same content is provided as textual tokens. We systematica…
FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights
Zhen Wang, Fan Bai, Zhongyan Luo +9
Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery r…
Task Matters: Knowledge Requirements Shape LLM Responses to Context-Memory Conflict
Kaiser Sun, Fan Bai, Mark Dredze
Large language models (LLMs) draw on both contextual information and parametric memory, yet these sources can conflict. Prior studies have largely examined this issue in contextual…
LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity Recognition
Fan Bai, Hamid Hassanzadeh, Ardavan Saeedi +1
In-context learning (ICL) enables large language models (LLMs) to perform new tasks using only a few demonstrations. However, in Named Entity Recognition (NER), existing ICL method…
Give me Some Hard Questions: Synthetic Data Generation for Clinical QA
Fan Bai, Keith Harrigian, Joel Stremmel +3
Clinical Question Answering (QA) systems enable doctors to quickly access patient information from electronic health records (EHRs). However, training these systems requires signif…
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
Xinyuan Wang, Chenxi Li, Zhen Wang +6
Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instinc…
Schema-Driven Information Extraction from Heterogeneous Tables
Fan Bai, Junmo Kang, Gabriel Stanovsky +3
In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extrac…
Few-Shot Anaphora Resolution in Scientific Protocols via Mixtures of In-Context Experts
Nghia T. Le, Fan Bai, Alan Ritter
Anaphora resolution is an important task for information extraction across a range of languages, text genres, and domains, motivating the need for methods that do not require large…
Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding
Janvijay Singh, Fan Bai, Zhen Wang
Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks. However, entity tracking on the procedural text has not benefited…
SynKB: Semantic Search for Synthetic Procedures
Fan Bai, Alan Ritter, Peter Madrid +2
In this paper we present SynKB, an open-source, automatically extracted knowledge base of chemical synthesis protocols. Similar to proprietary chemistry databases such as Reaxsys,…
Pre-train or Annotate? Domain Adaptation with a Constrained Budget
Fan Bai, Alan Ritter, Wei Xu
Recent work has demonstrated that pre-training in-domain language models can boost performance when adapting to a new domain. However, the costs associated with pre-training raise…
Process-Level Representation of Scientific Protocols with Interactive Annotation
Ronen Tamari, Fan Bai, Alan Ritter +1
We develop Process Execution Graphs (PEG), a document-level representation of real-world wet lab biochemistry protocols, addressing challenges such as cross-sentence relations, lon…
Structured Minimally Supervised Learning for Neural Relation Extraction
Fan Bai, Alan Ritter
We present an approach to minimally supervised relation extraction that combines the benefits of learned representations and structured learning, and accurately predicts sentence-l…