Paper-Conference

NNOSE: Nearest Neighbor Occupational Skill Extraction
An EACL 2024 retrieval-augmented skill extraction method that uses nearest-neighbor datastores to improve rare and cross-dataset occupational skill prediction.
Cite URL
NNOSE: Nearest Neighbor Occupational Skill Extraction
ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Question
An ACM SAC 2024 analysis of ChatGPT for generating pre-university math questions, introducing the TopicMath curriculum collection.
PDF Cite Code
ChatGPT as a Math Questioner? Evaluating ChatGPT on Generating Pre-university Math Question
Self-Evaluation Guided Beam Search for Reasoning
A NeurIPS 2023 decoding algorithm that guides LLM reasoning with stepwise self-evaluation.
PDF Cite Code Project Poster Slides DOI NeurIPS OpenReview
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
A human-LLM co-annotation framework that allocates labeling work by uncertainty.
Cite DOI URL
CoAnnotating: Uncertainty-Guided Work Allocation between Human and Large Language Models for Data Annotation
CocoSciSum: A Scientific Summarization Toolkit with Compositional Controllability
A controllable scientific summarization toolkit that lets users steer length and keyword inclusion.
Cite DOI URL
CocoSciSum: A Scientific Summarization Toolkit with Compositional Controllability
Doolittle: Benchmarks and Corpora for Academic Writing Formalization
A benchmark and training framework for paragraph-level academic writing formalization.
Cite DOI URL
Doolittle: Benchmarks and Corpora for Academic Writing Formalization
ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning
A visio-linguistic dataset and chain-of-thought framework for human-centric event causality inference.
Cite DOI URL
ECHo: A Visio-Linguistic Dataset for Event Causality Inference via Human-Centric Reasoning
On the Risk of Misinformation Pollution with Large Language Models
An analysis of how LLM-generated misinformation can harm QA systems, with mitigation strategies.
Cite DOI URL
On the Risk of Misinformation Pollution with Large Language Models
QACheck: A Demonstration System for Question-Guided Multi-Hop Fact-Checking
A question-guided multi-hop fact-checking demo system that explains its reasoning through Q&A traces.
Cite DOI URL
QACheck: A Demonstration System for Question-Guided Multi-Hop Fact-Checking
SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables
A scientific table benchmark for compositional reasoning and claim verification.
Cite DOI URL
SCITAB: A Challenging Benchmark for Compositional Reasoning and Claim Verification on Scientific Tables