Papers by Yisi Sang

10 papers
TVShowGuess: Character Comprehension in Stories as Speaker Guessing (2022.naacl-main)

Copied to clipboard

Challenge: Our proposed task, TVShowGuess, builds on the scripts of TV series and takes the form of guessing the anonymous main characters based on the backgrounds of the scenes and the dialogues.
Approach: They propose a task that takes the form of guessing the anonymous main characters based on the backgrounds of the scenes and the dialogues.
Outcome: The proposed models outperform baselines, yet lag behind human performance.
FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge (2023.emnlp-demo)

Copied to clipboard

Challenge: Existing large language models (LLMs) have a tendency to hallucinate and provide creative and fluent responses that are not factually accurate.
Approach: They propose a tool that automatically extracts factual claims from text, gathers evidence from external knowledge sources, evaluates the factuality of each claim, and suggests revisions for identified errors.
Outcome: The proposed tool detects errors in text and evaluates their factuality and suggests revisions based on the collected evidence.
Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension (2022.acl-long)

Copied to clipboard

Challenge: Existing QA datasets rarely distinguish fine-grained reading skills, such as the understanding of varying narrative elements.
Approach: They propose to use FairytaleQA to generate 10,580 questions based on 278 children-friendly stories to assess model's fine-grained learning skills.
Outcome: The proposed dataset consists of 10,580 questions derived from 278 children-friendly stories, covering seven types of narrative elements or relations.
Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026.acl-long)

Copied to clipboard

Challenge: Tool-calling agents are increasingly deployed in real-world customer-facing workflows . but most studies on tool-callers focus on idealized settings with general, fixed, and well-specified tasks.
Approach: They propose a tool-calling agent-based data pipeline that converts trajectories into user-facing tasks with controlled intent adaptations.
Outcome: The proposed pipeline can be used to study tool use under three scenarios.
LLMs for Now, Fine-Tuning for Later: An Ensemble Approach to Data Drift in Domain-Specific Tasks (2026.acl-srw)

Copied to clipboard

Challenge: Deploying machine learning models in domain-specific scenarios is challenged by data drift and the scarcity of expert annotations.
Approach: They propose a system that combines an LLM, an AL-assisted compact model and an automatic switch module to assist the active learning process.
Outcome: The proposed system achieves 96–98% switch accuracy and outperforms both models used alone.
Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data (2026.acl-long)

Copied to clipboard

Challenge: Recent research shows that LLM Agents can generate “believable” human behaviors via prompt-only methods, leaving open questions of whether they can accurately generate step-by-step actions in multi-turn interaction tasks.
Approach: They propose to use shopping data to evaluate LLMs' ability to accurately generate step-by-step actions in a multi-turn interaction task.
Outcome: The proposed model achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing improvements of 5.4% and 13.85% over baselines.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

Copied to clipboard

Challenge: Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach: They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome: The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.
More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Sampling (2024.findings-naacl)

Copied to clipboard

Challenge: Existing studies on LLM prompting focus on selecting a better set of data samples inside one single prompt input, but why not design and leverage multiple ICL prompts together to further improve the LLM’s performance?
Approach: They propose a low-resource LLM prompting technique to optimize the construction of multiple ICL prompt inputs to produce confident predictions.
Outcome: The proposed technique can produce confident predictions by optimizing the construction of multiple ICL prompt inputs on four NLI datasets and one QA dataset.
ConvKGYarn: Spinning Configurable and Scalable Conversational Knowledge Graph QA Datasets with Large Language Models (2024.emnlp-industry)

Copied to clipboard

Challenge: Knowledge Graphs (KGs) are a powerful tool for capturing structured representations of the world.
Approach: They propose a scalable method for generating up-to-date and configurable conversational KGQA datasets that adheres to human interaction configurations and operates at a significantly larger scale.
Outcome: Qualitative psychometric analyses show that ConvKGYarn produces high-quality data comparable to popular conversational KGQA datasets across various metrics.
MBTI Personality Prediction for Fictional Characters Using Movie Scripts (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing NLP models cannot predict character's personality types based on text classifications . character comprehension is the cornerstone of understanding stories in psychology and education.
Approach: They propose a benchmark to predict movie character's MBTI or Big 5 personality types based on the narratives of the character.
Outcome: The proposed model outperforms existing models in the task and is more accurate than random guesses.

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