Few-shot Reranking for Multi-hop QA via Language Model Prompting

• URL: http://arxiv.org/abs/2205.12650v3
• Date: Sun, 2 Jul 2023 18:32:21 GMT
• Title: Few-shot Reranking for Multi-hop QA via Language Model Prompting
• Authors: Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang
• Abstract summary: We study few-shot reranking for multi-hop QA with open-domain questions. We propose PromptRank, which relies on large language models prompting for multi-hop path reranking. PromptRank yields strong retrieval performance on HotpotQA with only 128 training examples.
• Score: 56.454088569241534
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study few-shot reranking for multi-hop QA with open-domain questions. To alleviate the need for a large number of labeled question-document pairs for retriever training, we propose PromptRank, which relies on large language models prompting for multi-hop path reranking. PromptRank first constructs an instruction-based prompt that includes a candidate document path and then computes the relevance score between a given question and the path based on the conditional likelihood of the question given the path prompt according to a language model. PromptRank yields strong retrieval performance on HotpotQA with only 128 training examples compared to state-of-the-art methods trained on thousands of examples -- 73.6 recall@10 by PromptRank vs. 77.8 by PathRetriever and 77.5 by multi-hop dense retrieval. Code available at https://github.com/mukhal/PromptRank

Related papers

• Multimodal Reranking for Knowledge-Intensive Visual Question Answering [77.24401833951096]
  We introduce a multi-modal reranker to improve the ranking quality of knowledge candidates for answer generation. Experiments on OK-VQA and A-OKVQA show that multi-modal reranker from distant supervision provides consistent improvements.
  arXiv  Detail & Related papers  (2024-07-17T02:58:52Z)
• BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval [54.54576644403115]
  Many complex real-world queries require in-depth reasoning to identify relevant documents. We introduce BRIGHT, the first text retrieval benchmark that requires intensive reasoning to retrieve relevant documents. Our dataset consists of 1,384 real-world queries spanning diverse domains, such as economics, psychology, mathematics, and coding.
  arXiv  Detail & Related papers  (2024-07-16T17:58:27Z)
• Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversational Search [25.16282868262589]
  RetPO is designed to optimize a language model (LM) for reformulating search queries in line with the preferences of the target retrieval systems. We construct a large-scale dataset called Retrievers' Feedback on over 410K query rewrites across 12K conversations. The resulting model achieves state-of-the-art performance on two recent conversational search benchmarks.
  arXiv  Detail & Related papers  (2024-02-19T04:41:31Z)
• UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph [89.98762327725112]
  Multi-hop Question Answering over Knowledge Graph(KGQA) aims to find the answer entities that are multiple hops away from the topic entities mentioned in a natural language question. We propose UniKGQA, a novel approach for multi-hop KGQA task, by unifying retrieval and reasoning in both model architecture and parameter learning.
  arXiv  Detail & Related papers  (2022-12-02T04:08:09Z)
• Few-shot Multi-hop Question Answering over Knowledge Base [0.0]
  This paper proposes an efficient pipeline method equipped with a pre-trained language model and a strategy to construct artificial training samples. We evaluate our model on CCKS 2019 Complex Question Answering via Knowledge Base task and achieves F1-score of 62.55% on the test dataset.
  arXiv  Detail & Related papers  (2021-12-14T00:56:54Z)
• Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answering [32.69969157825044]
  We propose a new architecture that models paragraphs as sequential data and considers multi-hop information retrieval as a kind of sequence labeling task. We evaluate our method on both full wiki and distractor subtask of HotpotQA, a public textual multi-hop QA dataset.
  arXiv  Detail & Related papers  (2021-02-07T08:15:51Z)
• Multi-hop Question Generation with Graph Convolutional Network [58.31752179830959]
  Multi-hop Question Generation (QG) aims to generate answer-related questions by aggregating and reasoning over multiple scattered evidence from different paragraphs. We propose Multi-Hop volution Fusion Network for Question Generation (MulQG), which does context encoding in multiple hops. Our proposed model is able to generate fluent questions with high completeness and outperforms the strongest baseline by 20.8% in the multi-hop evaluation.
  arXiv  Detail & Related papers  (2020-10-19T06:15:36Z)
• Answering Any-hop Open-domain Questions with Iterative Document Reranking [62.76025579681472]
  We propose a unified QA framework to answer any-hop open-domain questions. Our method consistently achieves performance comparable to or better than the state-of-the-art on both single-hop and multi-hop open-domain QA datasets.
  arXiv  Detail & Related papers  (2020-09-16T04:31:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.