Papers with out-of-domain evaluation
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? (2022.findings-emnlp)
Copied to clipboard
Xilun Chen, Kushal Lakhotia, Barlas Oguz, Anchit Gupta, Patrick Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta, Wen-tau Yih
| 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. |