Papers with out-of-domain evaluation

3 papers
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing sparse retrievers lack the ability to match salient phrases and rare entities in the query.
Approach: They introduce a dense Lexical Model that can be trained to imitate a sparse one.
Outcome: The proposed model outperforms sparse retrievers on a range of tasks including five question answering datasets and the MS MARCO passage retrieval.
Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training (2023.eacl-main)

Copied to clipboard

Challenge: Large-scale vision-language pre-trained (VLP) models generate unfaithful or nonsensical texts given the source input, which is called hallucination.
Approach: They propose a VLP loss-based model to mitigate object hallucination by decoupling VLP objectives and a token-level image-text alignment.
Outcome: The proposed model reduces object hallucination by 17.4% on two benchmarks.
Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations (2024.findings-emnlp)

Copied to clipboard

Challenge: Structured chain-of-thought (SCoT) prompting is used to generate content-grounded multi-turn questions and answers with a large language model.
Approach: They propose a structured chain-of-thought prompting approach to generating content-grounded multi-turn question-answer conversations with a pre-trained large language model.
Outcome: The proposed approach increases agent faithfulness to grounding documents by 16.8% when used as training data.

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