Lost in Formatting: How Output Formats Skew LLM Performance on Information Extraction
Published in EACL 2026, 2026
This paper shows how output formats skew LLM performance on IE.
Posts by Collection
portfolio
publications
When Tasks Share Structure: A Comparative Study of Training Strategies for Generative Event Extraction
Published in ACL 2026 EEUCA, 2026
A comparative study of training strategies for generative event extraction.
ReciFine: Finely Annotated Recipe Dataset for Controllable Recipe Generation
Published in EACL 2026, 2026
Finely Annotated Recipe Dataset for Controllable Recipe Generation.
ReciLink: Zero-shot Linking of Recipe Entities through Definition Alignment and Embedding Learning
Published in Submitted to EMNLP 2026, 2026
Zero-shot Linking of Recipe Entities through Definition Alignment and Embedding Learning.
Cultural Adaptation of Recipes for Low-Resource Languages: A Benchmark and Multilingual Culinary Lexicon
Published in Submitted to EMNLP 2026, 2026
A Benchmark and Multilingual Culinary Lexicon.
LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm
Published in arXiv, 2026
A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm.