Papers by Fan Bai

20 papers
Task Matters: Knowledge Requirements Shape LLM Responses to Context–Memory Conflict (2026.findings-acl)

Copied to clipboard

Challenge: Prior work has shown that large language models favor parametric knowledge under conflict, but this setting assumes that tasks should always rely on the provided passage.
Approach: They propose a model-agnostic diagnostic framework that holds underlying knowledge constant while injecting controlled conflicts across tasks with varying knowledge requirements.
Outcome: Evaluating representative open-source LLMs, the proposed framework holds underlying knowledge constant while injecting controlled conflicts across tasks with varying knowledge requirements.
LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity Recognition (2025.emnlp-main)

Copied to clipboard

Challenge: Named Entity Recognition (NER) tasks are performed using only a few demonstrations.
Approach: They propose a method that leverages training labels through token-level statistics to improve ICL performance.
Outcome: The proposed method outperforms existing methods on five NER datasets and is robust in low-resource settings.
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directions (2025.findings-emnlp)

Copied to clipboard

Challenge: Conceptualization is a fundamental element of human cognition and plays a pivotal role in generalizable reasoning.
Approach: They propose to categorize different types of conceptualizations into four levels based on the types of instances being conceptualized.
Outcome: The proposed categorization of different types of conceptualizations into four levels based on the types of instances being conceptualized .
MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media (2025.emnlp-main)

Copied to clipboard

Challenge: Social media is a key platform for emotional expression, yet deep learning lacks flexibility and interpretability.
Approach: They propose to use Chinese social media to train interpretable mental health instruction datasets to test models' ability to explain their decisions.
Outcome: The proposed models outperform deep learning and LLMs on three mental health downstream tasks and demonstrate their potential for clinical applications.
Process-Level Representation of Scientific Protocols with Interactive Annotation (2021.eacl-main)

Copied to clipboard

Challenge: Existing efforts to automate wet lab workflows are focusing on graph-prediction models that capture both concrete, exact quantities ("30 minutes") and vague instructions ("swirl")
Approach: They manually annotate PEGs in a corpus of complex lab protocols with a novel interactive textual simulator that keeps track of entity traits and semantic constraints during annotation.
Outcome: The proposed graph-prediction models are good at entity identification and local relation extraction while addressing challenges such as cross-sentence relations and long-range coreference.
Text-to-TrajVis: Enabling Trajectory Data Visualizations from Natural Language Questions (2026.findings-acl)

Copied to clipboard

Challenge: Existing datasets for this task are limited and there is no suitable one available.
Approach: They propose a new visualization language called Trajectory Visualization Language (TVL) to facilitate querying trajectory data and generating visualizations.
Outcome: The proposed language can be used to query and generate trajectory data and generate visualizations with large language models.
Conversational Recommender System and Large Language Model Are Made for Each Other in E-commerce Pre-sales Dialogue (2023.findings-emnlp)

Copied to clipboard

Challenge: E-commerce pre-sales dialogues elicit user needs and preferences for items . large language models lack domain-specific knowledge for accurate recommendations .
Approach: They propose two collaboration strategies to integrate CRS and large language models in pre-sales dialogues.
Outcome: The proposed methods can be very effective in some cases, the authors say .
Pre-train or Annotate? Domain Adaptation with a Constrained Budget (2021.emnlp-main)

Copied to clipboard

Challenge: Recent work shows that pre-training in-domain language models can boost performance when adapting to a new domain.
Approach: They propose to combine annotation and pre-training to maximize performance under budget constraints.
Outcome: The proposed approach is based on the annotation cost of three procedural text datasets and pre-training cost of 3 in-domain language models.
Schema-Driven Information Extraction from Heterogeneous Tables (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing work on information extraction from tables has focused on developing custom pipelines for each table collection.
Approach: They propose a task that transforms tabular data into structured records following a human-authored schema.
Outcome: The proposed task achieves F1 scores ranging from 74.2 to 96.1 while maintaining cost efficiency.
AutoSchemaKG: Autonomous Knowledge Graph Construction through Dynamic Schema Induction from Web-Scale Corpora (2026.acl-long)

Copied to clipboard

Challenge: Existing knowledge graph construction frameworks require predefined schemas, limiting their scalability and domain coverage.
Approach: They propose a framework for fully autonomous knowledge graph construction that eliminates the need for predefined schemas.
Outcome: The proposed framework outperforms state-of-the-art models on multi-hop QA tasks and enhances LLM factuality.
Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for structured generation of outputs are inefficient under large inference batches.
Approach: They propose a new LLM-based method that parses LR(1) grammars into a pushdown automaton and exploits deterministic pushdown automation to optimize the constrained LLM decoding efficiency.
Outcome: The proposed method improves time per output token (TPOT) by 40% and throughput by 36% .
FlowSearch: Advancing Deep Research with Dynamic Structured Knowledge Flow (2026.acl-long)

Copied to clipboard

Challenge: FlowSearch is a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Approach: They propose a multi-agent framework that actively constructs and evolves a dynamic structured knowledge flow to drive subtask execution and reasoning.
Outcome: The proposed framework achieves competitive performance on GAIA, HLE, GPQA and TRQA benchmarks and is available to download.
Explain the Synth: Interpretable Evaluation of LLM Data Synthesis (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly used to generate tabular data.
Approach: They propose a framework that uses a rule-based model as a shared explanatory language to examine the explanation of real versus synthetic data.
Outcome: The proposed framework compares the explanatory structure induced by real versus synthetic data.
Few-Shot Anaphora Resolution in Scientific Protocols via Mixtures of In-Context Experts (2022.findings-emnlp)

Copied to clipboard

Challenge: In-context learning has emerged as a promising approach to resolve anaphora, but there are challenges in applying it to scientific protocols.
Approach: They propose a method which combines predictions of hundreds of in-context experts and combines them to yield a 30% increase in F1 over a competitive prompt retrieval baseline.
Outcome: The proposed method yields 30% increase in F1 score over a competitive prompt retrieval baseline.
SynKB: Semantic Search for Synthetic Procedures (2022.emnlp-demos)

Copied to clipboard

Challenge: SynKB is an open-source, automatically extracted knowledge base of chemical synthesis protocols.
Approach: They propose to make SynKB available as an open-source tool for chemists . synKB supports more flexible queries about reaction conditions .
Outcome: The proposed open-source tool has higher recall and high precision than proprietary chemistry databases.
Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding (2023.eacl-main)

Copied to clipboard

Challenge: State-of-the-art entity tracking approaches either design complicated model architectures or rely on task-specific pre-training to achieve good results.
Approach: They propose a multi-task learning-enabled entity tracking approach that utilizes knowledge gained from general domain tasks to improve entity tracking.
Outcome: The proposed approach achieves state-of-the-art on two popular entity tracking datasets, even though it does not require any task-specific architecture design or pre-training.
Structured Minimally Supervised Learning for Neural Relation Extraction (N19-1)

Copied to clipboard

Challenge: Recent work shows that distant supervision can cause significant label noise when learning from large quantities of unlabeled text.
Approach: They propose a method that combines the benefits of learning representations and structured learning to predict sentence-level relation mentions given only proposition-level supervision from a KB.
Outcome: The proposed approach outperforms a number of baseline approaches while minimizing label noise.
Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning (2026.acl-long)

Copied to clipboard

Challenge: elucidating scaling laws for large language models (LLMs) during pre-training remains unexplored.
Approach: They characterize how model scale, data, and compute interact during pre-training . they find that large models consistently demonstrate superior compute and data efficiency .
Outcome: The proposed scaling laws offer practical guidance for scaling reasoning capabilities through reinforcement learning post-training.
Easy and Efficient Transformer: Scalable Inference Solution For Large NLP Model (2022.naacl-industry)

Copied to clipboard

Challenge: Recent studies show that transformer-based models are effective over many tasks, but they are expensive to deploy in the industrial application.
Approach: They propose a transformer-based inference solution that optimizes kernels for long inputs and large hidden sizes and a flexible CUDA memory manager to reduce the memory footprint when deploying a large model.
Outcome: The proposed solution achieves an average speedup of 1.40-4.20x on the transformer decoder layer with an A100 GPU.

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