An official website of the United States government
While dense retrieval has been shown to be effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance labels are available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings (HyDE). Given a query, HyDE first zero-shot prompts an instruction-following language model (e.g., InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is “fake” and may contain hallucinations. Then, an unsupervised contrastively learned encoder (e.g., Contriever) encodes the document into an embedding vector. This vector identifies a neighborhood in the corpus embedding space, from which similar real documents are retrieved based on vector similarity. This second step grounds the generated document to the actual corpus, with the encoder’s dense bottleneck filtering out the hallucinations. Our experiments show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever and shows strong performance comparable to fine-tuned retrievers across various tasks (e.g. web search, QA, fact verification) and in non-English languages (e.g., sw, ko, ja, bn).
more »
« less
This content will become publicly available on April 1, 2026
Open-World Evaluation for Retrieving Diverse Perspectives
We study retrieving a set of documents that covers various perspectives on a complex and contentious question (e.g., will ChatGPT do more harm than good?). We curate a Benchmark for Retrieval Diversity for Subjective questions (BERDS), where each example consists of a question and diverse perspectives associated with the question, sourced from survey questions and debate websites. On this data, retrievers paired with a corpus are evaluated to surface a document set that contains diverse perspectives. Our framing diverges from most retrieval tasks in that document relevancy cannot be decided by simple string matches to references. Instead, we build a language model-based automatic evaluator that decides whether each retrieved document contains a perspective. This allows us to evaluate the performance of three different types of corpus (Wikipedia, web snapshot, and corpus constructed on the fly with retrieved pages from the search engine) paired with retrievers. Retrieving diverse documents remains challenging, with the outputs from existing retrievers covering all perspectives on only 33.74% of the examples. We further study the impact of query expansion and diversity-focused reranking approaches and analyze retriever sycophancy. Together, we lay the foundation for future studies in retrieval diversity handling complex queries.
more »
« less
- Award ID(s):
- 2521091
- PAR ID:
- 10617279
- Publisher / Repository:
- Association for Computational Linguistics
- Date Published:
- Page Range / eLocation ID:
- 8508 to 8528
- Format(s):
- Medium: X
- Location:
- Albuquerque, New Mexico
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Given a private string q and a remote server that holds a set of public documents D, how can one of the K most relevant documents to q in D be selected and viewed without anyone (not even the server) learning anything about q or the document? This is the oblivious document ranking and retrieval problem. In this paper, we describe Coeus, a system that solves this problem. At a high level, Coeus composes two cryptographic primitives: secure matrix-vector product for scoring document relevance using the widely-used term frequency-inverse document frequency (tf-idf) method, and private information retrieval (PIR) for obliviously retrieving documents. However, Coeus reduces the time to run these protocols, thereby improving the user-perceived latency, which is a key performance metric. Coeus first reduces the PIR overhead by separating out private metadata retrieval from document retrieval, and it then scales secure matrix-vector product to tf-idf matrices with several hundred billion elements through a series of novel cryptographic refinements. For a corpus of English Wikipedia containing 5 million documents, a keyword dictionary with 64K keywords, and on a cluster of 143 machines on AWS, Coeus enables a user to obliviously rank and retrieve a document in 3.9 seconds---a 24x improvement over a baseline system.more » « less
-
null (Ed.)Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, in particular, conversational search systems with limited bandwidth interfaces. Analyzing and generating clarifying question have been recently studied in the literature. However, accurate utilization of user responses to clarifying questions has been relatively less explored. In this paper, we propose a neural network model based on a novel attention mechanism, called multi source attention network. Our model learns a representation for a user-system conversation that includes clarifying questions. In more detail, with the help of multiple information sources, our model weights each term in the conversation. In our experiments, we use two separate external sources, including the top retrieved documents and a set of different possible clarifying questions for the query. We implement the proposed representation learning model for two downstream tasks in conversational search; document retrieval and next clarifying question selection. We evaluate our models using a public dataset for search clarification. Our experiments demonstrate significant improvements compared to competitive baselines.more » « less
-
Chua, Tat-Seng; Ngo, Chong-Wah; Kumar, Ravi; Lauw, Hady W; Lee, Roy Ka-Wei (Ed.)Document retrieval has greatly benefited from the advancements of large-scale pre-trained language models (PLMs). However, their effectiveness is often limited in theme-specific applications for specialized areas or industries, due to unique terminologies, incomplete contexts of user queries, and specialized search intents. To capture the theme-specific information and improve retrieval, we propose to use a corpus topical taxonomy, which outlines the latent topic structure of the corpus while reflecting user-interested aspects. We introduce ToTER (Topical Taxonomy Enhanced Retrieval) framework, which identifies the central topics of queries and documents with the guidance of the taxonomy, and exploits their topical relatedness to supplement missing contexts. As a plug-and-play framework, ToTER can be flexibly employed to enhance various PLM-based retrievers. Through extensive quantitative, ablative, and exploratory experiments on two real-world datasets, we ascertain the benefits of using topical taxonomy for retrieval in theme-specific applications and demonstrate the effectiveness of ToTER.more » « less
-
Retrieving evidence to support or refute claims is a core part of automatic fact-checking. Prior work makes simplifying assumptions in retrieval that depart from real-world use cases: either no access to evidence, access to evidence curated by a human fact-checker, or access to evidence published after a claim was made. In this work, we present the first realistic pipeline to check real-world claims by retrieving raw evidence from the web. We restrict our retriever to only search documents available prior to the claim’s making, modeling the realistic scenario of emerging claims. Our pipeline includes five components: claim decomposition, raw document retrieval, fine-grained evidence retrieval, claim-focused summarization, and veracity judgment. We conduct experiments on complex political claims in the ClaimDecomp dataset and show that the aggregated evidence produced by our pipeline improves veracity judgments. Human evaluation finds the evidence summary produced by our system is reliable (it does not hallucinate information) and relevant to answering key questions about a claim, suggesting that it can assist fact-checkers even when it does not reflect a complete evidence set.more » « less
