Information Extraction

GKG-LLM: Unifying Knowledge Graph Construction with a novel 3-stage framework, empowering domain adaptation & resource efficiency.

PLM retrievers overrate low-perplexity docs, causing source bias. This paper reveals the causal effect & offers a fix!

IFIR: a new benchmark for instruction-following retrieval in expert domains, revealing current model limitations.

Cuckoo: a novel information extraction (IE) model leverages LLM pre-training data, achieving superior performance in few-shot settings by reframing next-token prediction as token extraction.

OneKE: a dockerized, schema-guided LLM agent system efficiently extracts knowledge from diverse sources, offering adaptability and robust error handling.

LongKey: A novel framework excels at extracting keyphrases from lengthy documents using an encoder-based language model and max-pooling, outperforming existing methods across diverse datasets.

RetrieveGPT enhances code-mixed information retrieval by merging GPT-3.5 Turbo prompts with a novel mathematical model, improving the accuracy of relevant document extraction from complex, sequenced c…