Papers with few-shot in-context learning
Massively Multilingual Instruction-Following Information Extraction (2025.findings-acl)
Copied to clipboard
| Challenge: | Past literature on information extraction (IE) has focused on a few high-resource languages, hindering their applications on multilingual corpora. |
| Approach: | They propose a collection of data that unifies and standardizes instruction-following multilingual IE and introduce a structure-aware metric that captures partially matched spans. |
| Outcome: | The proposed framework standardizes and unifies 215 manually annotated datasets, covering 96 typologically diverse languages from 18 language families. |
Interactive-KBQA: Multi-Turn Interactions for Knowledge Base Question Answering with Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Knowledge base question answering (KBQA) is a challenging task, particularly in parsing intricate questions into executable logical forms. |
| Approach: | They propose a framework to generate logical forms through direct interaction with knowledge bases (KBs) by annotating a dataset with step-wise reasoning processes. |
| Outcome: | The proposed framework achieves competitive results on the WebQuestionsSP, ComplexWebQuestIONS, KQA Pro, and MetaQA datasets with a minimal number of examples (shots). Importantly, the proposed model supports manual intervention, allowing for the iterative refinement of LLM outputs. |
ParaICL: Towards Parallel In-Context Learning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to improve ICL performance are limited by the length of the input context. |
| Approach: | They propose a method that utilizes all demonstration examples without exceeding the manageable context length. |
| Outcome: | The proposed method can be scaled up to integrate with existing methods. |
Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition (2024.emnlp-main)
Copied to clipboard
| Challenge: | Prior research addresses generating attributions alongside responses in open domains, either per sentence or per paragraph. |
| Approach: | They propose a method to decompose generated answers for attribution using template-based in-context learning. |
| Outcome: | The proposed approach enhances the semantic understanding of abstractive and extractive answers. |