本文提出了大语言模型辅助检索模型排序（Large Language Model Assisted Retrieval Model Ranking，LARMOR），这是一种高效的无监督方法，借助大语言模型（LLMs）选择适用于测试语料库（目标语料）的稠密检索器。对于众多依赖在公开语料上训练的稠密检索器来编码或检索全新私有目标语料的信息检索（IR）应用而言，稠密检索器的选择至关重要。这是因为当出现域偏移——即目标语料的下游语料、领域或任务与稠密检索器训练时的领域/任务存在差异时，检索器性能通常会下降。此外，当目标语料无标注时（例如零样本场景），直接在目标语料上评估模型并不可行，因此无监督地选择效果最优的预训练稠密检索器成为一项关键挑战。现有的稠密检索器选择方法不足以应对存在域偏移的场景。我们提出的解决方案利用LLMs，基于从目标语料中采样的一组文档生成伪相关查询、标签和参考列表，随后根据稠密检索器在这些生成的伪相关信号上的表现对其进行排序。值得注意的是，我们的方法是首个仅依赖目标语料的方法，无需训练语料也无需测试标签。为评估方法的有效性，我们构建了一个包含大量前沿稠密检索器的池。所提方法在稠密检索器选择和排序两个任务上均优于现有基线方法。我们已将代码和结果公开在https://github.com/ielab/larmor/。
英文摘要：
In this paper we present Large Language Model Assisted Retrieval Model Ranking (LARMOR), an effective unsupervised approach that leverages LLMs for selecting which dense retriever to use on a test corpus (target). Dense retriever selection is crucial for many IR applications that rely on using dense retrievers trained on public corpora to encode or search a new, private target corpus. This is because when confronted with domain shift, where the downstream corpora, domains, or tasks of the target corpus differ from the domain/task the dense retriever was trained on, its performance often drops. Furthermore, when the target corpus is unlabeled, e.g., in a zero-shot scenario, the direct evaluation of the model on the target corpus becomes unfeasible. Unsupervised selection of the most effective pre-trained dense retriever becomes then a crucial challenge. Current methods for dense retriever selection are insufficient in handling scenarios with domain shift. Our proposed solution leverages LLMs to generate pseudo-relevant queries, labels and reference lists based on a set of documents sampled from the target corpus. Dense retrievers are then ranked based on their effectiveness on these generated pseudo-relevant signals. Notably, our method is the first approach that relies solely on the target corpus, eliminating the need for both training corpora and test labels. To evaluate the effectiveness of our method, we construct a large pool of state-of-the-art dense retrievers. The proposed approach outperforms existing baselines with respect to both dense retriever selection and ranking. We make our code and results publicly available at https://github.com/ielab/larmor/.
Neural ranking models (NRMs) have become one of the most important techniques in information retrieval (IR). Due to the limitation of relevance labels, the training of NRMs heavily relies on negative sampling over unlabeled data. In general machine learning scenarios, it has shown that training with hard negatives (i.e., samples that are close to positives) could lead to better performance. Surprisingly, we find opposite results from our empirical studies in IR. When sampling top-ranked results (excluding the labeled positives) as negatives from a stronger retriever, the performance of the lea…
University of Science and Technology of China（中国科学技术大学）；University of Electronic Science and Technology of China（电子科技大学）；Microsoft Research Asia（微软亚洲研究院）
Deep recommender systems (DRS) are intensively applied in modern web services. To deal with the massive web contents, DRS employs a two-stage workflow: retrieval and ranking, to generate its recommendation results. The retriever aims to select a small set of relevant candidates from the entire items with high efficiency; while the ranker, usually more precise but time-consuming, is supposed to further refine the best items from the retrieved candidates. Traditionally, the two components are trained either independently or within a simple cascading pipeline, which is prone to poor collaboration…
University of California, San Diego（加州大学圣地亚哥分校）；Microsoft Research Asia（微软亚洲研究院）；Sun Yat-sen University（中山大学）
In this paper, we propose LaPraDoR, a pretrained dual-tower dense retriever that does not require any supervised data for training. Specifically, we first present Iterative Contrastive Learning (ICoL) that iteratively trains the query and document encoders with a cache mechanism. ICoL not only enlarges the number of negative instances but also keeps representations of cached examples in the same hidden space. We then propose Lexicon-Enhanced Dense Retrieval (LEDR) as a simple yet effective way to enhance dense retrieval with lexical matching. We evaluate LaPraDoR on the recently proposed BEIR …
Literature search is critical for any scientific research. Different from Web or general domain search, a large portion of queries in scientific literature search are entity-set queries, that is, multiple entities of possibly different types. Entity-set queries reflect user's need for finding documents that contain multiple entities and reveal inter-entity relationships and thus pose non-trivial challenges to existing search algorithms that model each entity separately. However, entity-set queries are usually sparse (i.e., not so repetitive), which makes ineffective many supervised ranking mod…
Dense retrievers encode queries and documents and map them in an embedding space using pre-trained language models. These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense retrievers. However, these high-dimensional embeddings lead to larger index storage and higher retrieval latency. To reduce the embedding dimensions of dense retrieval, this paper proposes a Conditional Autoencoder (ConAE) to compress the high-dimensional embeddings to maintain the same embedding distribution and better recover the ranking features. Our experime…
Pseudo Relevance Feedback (PRF) is known to improve the effectiveness of bag-of-words retrievers. At the same time, deep language models have been shown to outperform traditional bag-of-words rerankers. However, it is unclear how to integrate PRF directly with emergent deep language models. In this article, we address this gap by investigating methods for integrating PRF signals into rerankers and dense retrievers based on deep language models. We consider text-based and vector-based PRF approaches, and investigate different ways of combining and scoring relevance signals. An extensive empiric…
GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases
Department of Electrical Engineering and Computer Science, University of Michigan（密歇根大学电气工程与计算机科学系）；Department of Computational Medicine and Bioinformatics, University of Michigan（密歇根大学计算医学与生物信息学系）
Pseudo-Relevance Feedback (PRF) utilises the relevance signals from the top-k passages from the first round of retrieval to perform a second round of retrieval aiming to improve search effectiveness. A recent research direction has been the study and development of PRF methods for deep language models based rankers, and in particular in the context of dense retrievers. Dense retrievers, compared to more complex neural rankers, provide a trade-off between effectiveness, which is often reduced compared to more complex neural rankers, and query latency, which also is reduced making the retrieval …
In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to work well. Meanwhile, there has been a growing interest in learning sparse representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes. In this work, we present a new first-stage ranker based on explicit sparsity regularization and a…
Language Technologies Institute（语言技术研究所）；Carnegie Mellon University（卡内基梅隆大学）
Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full potential. In this paper, we identify and address two underlying problems of dense retrievers: i)~fragility to training data noise and ii)~requiring large batches to robustly learn the embedding space. We use the recently proposed Condenser pre-training architecture, which learns to condense information into the dense vector through LM pre-training. On top of i…
In this paper, we investigate the integration of sentence position and semantic role of words in a PageRank system to build a key phrase ranking method. We present the evaluation results of our approach on three scientific articles. We show that semantic role information, when integrated with a PageRank system, can become a new lexical feature. Our approach had an overall improvement on all the data sets over the state-of-art baseline approaches.
Text retrieval using learned dense representations has recently emerged as a promising alternative to "traditional" text retrieval using sparse bag-of-words representations. One recent work that has garnered much attention is the dense passage retriever (DPR) technique proposed by Karpukhin et al. (2020) for end-to-end open-domain question answering. We present a replication study of this work, starting with model checkpoints provided by the authors, but otherwise from an independent implementation in our group's Pyserini IR toolkit and PyGaggle neural text ranking library. Although our experi…
A generalized ensemble model (gEnM) for document ranking is proposed in this paper. The gEnM linearly combines basis document retrieval models and tries to retrieve relevant documents at high positions. In order to obtain the optimal linear combination of multiple document retrieval models or rankers, an optimization program is formulated by directly maximizing the mean average precision. Both supervised and unsupervised learning algorithms are presented to solve this program. For the supervised scheme, two approaches are considered based on the data setting, namely batch and online setting. I…
Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result, retrieval performance is restricted by semantic discrepancies and vocabulary gaps. On the other hand, transformer-based dense retrievers introduce significant improvements in information retrieval tasks by exploiting low-dimensional contextualized representations of the corpus. While dense retrievers are known for their relative effectiveness, they suffer from low…
Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However, current dense retrievers require splitting documents into short passages that usually contain local, partial, and sometimes biased context, and highly depend on the splitting process. As a consequence, it may yield inaccurate and misleading hidden representations, thus deteriorating the final retrieval result. In this work, we propose Dense Hierarchical Retrieva…
Dense retrieval is becoming one of the standard approaches for document and passage ranking. The dual-encoder architecture is widely adopted for scoring question-passage pairs due to its efficiency and high performance. Typically, dense retrieval models are evaluated on clean and curated datasets. However, when deployed in real-life applications, these models encounter noisy user-generated text. That said, the performance of state-of-the-art dense retrievers can substantially deteriorate when exposed to noisy text. In this work, we study the robustness of dense retrievers against typos in the …
Route Me If You Can: A Benchmark for Query Reformulation Selection
Toronto Metropolitan University（多伦多都会大学）；University of California, Berkeley（加州大学伯克利分校）；University of Waterloo（滑铁卢大学）；Mila - Quebec AI Institute（魁北克人工智能研究所）；University of Toronto（多伦多大学）
State of the art approaches for (embedding based) unsupervised semantic search exploits either compositional similarity (of a query and a passage) or pair-wise word (or term) similarity (from the query and the passage). By design, word based approaches do not incorporate similarity in the larger context (query/passage), while compositional similarity based approaches are usually unable to take advantage of the most important cues in the context. In this paper we propose a new compositional similarity based approach, called variable centroid vector (VCVB), that tries to address both of these li…
Seek: Self-Evaluative Exploration for Knowledge Retrieval
University of Waterloo（滑铁卢大学）；Mila – Quebec AI Institute（魁北克人工智能研究所）；University of California, Berkeley（加州大学伯克利分校）；University of Toronto（多伦多大学）；Toronto Metropolitan University（多伦多都会大学）
This paper presents Semantic SentenceRank (SSR), an unsupervised scheme for automatically ranking sentences in a single document according to their relative importance. In particular, SSR extracts essential words and phrases from a text document, and uses semantic measures to construct, respectively, a semantic phrase graph over phrases and words, and a semantic sentence graph over sentences. It applies two variants of article-structure-biased PageRank to score phrases and words on the first graph and sentences on the second graph. It then combines these scores to generate the final score for …
Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning approaches have succeeded in obtaining features appropriate for classification of multimedia data. However, unsupervised learning of feature representations adapted to content-based matching, comparison, or retrieval of multimedia data has not been explored well. To obtain such retrieval-adapted features, we introduce the idea of combining diffusion distance on a…
ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance
Department of Computer Science and Technology, Northeastern University, China（东北大学计算机科学与技术系）；Department of Computer Science and Technology, Institute for AI, Tsinghua University, China（清华大学人工智能研究院计算机科学与技术系）；Beijing National Research Center for Information Science and Technology, China（北京信息科学与技术国家研究中心）
Revela: Dense Retriever Learning via Language Modeling
Technical University of Darmstadt（达姆施塔特技术大学）；University of Washington（华盛顿大学）；Carnegie Mellon University（卡内基梅隆大学）；Microsoft（微软）；Tencent AI Lab（腾讯人工智能实验室）
Meta AI Research（Meta人工智能研究院）；Ecole normale supérieure, PSL University（巴黎文理研究大学高等师范学院）；Inria（法国国家信息与自动化研究所）；Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；University College London（伦敦大学学院）
Recently, information retrieval has seen the emergence of dense retrievers, using neural networks, as an alternative to classical sparse methods based on term-frequency. These models have obtained state-of-the-art results on datasets and tasks where large training sets are available. However, they do not transfer well to new applications with no training data, and are outperformed by unsupervised term-frequency methods such as BM25. In this work, we explore the limits of contrastive learning as a way to train unsupervised dense retrievers and show that it leads to strong performance in various…
$\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity
Technical University of Darmstadt（达姆施塔特工业大学）；Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）；University of Pennsylvania（宾夕法尼亚大学）；Tencent AI Lab（腾讯AI实验室）
The proliferation of massive open online courses (MOOCs) demands an effective way of course recommendation for jobs posted in recruitment websites, especially for the people who take MOOCs to find new jobs. Despite the advances of supervised ranking models, the lack of enough supervised signals prevents us from directly learning a supervised ranking model. This paper proposes a general automated weak supervision framework AutoWeakS via reinforcement learning to solve the problem. On the one hand, the framework enables training multiple supervised ranking models upon the pseudo labels produced …
The correlation of the result lists provided by search engines is fundamental and it has deep and multidisciplinary ramifications. Here, we present automatic and unsupervised methods to assess whether or not search engines provide results that are comparable or correlated. We have two main contributions: First, we provide evidence that for more than 80% of the input queries - independently of their frequency - the two major search engines share only three or fewer URLs in their search results, leading to an increasing divergence. In this scenario (divergence), we show that even the most robust…
Fast similarity search is a key component in large-scale information retrieval, where semantic hashing has become a popular strategy for representing documents as binary hash codes. Recent advances in this area have been obtained through neural network based models: generative models trained by learning to reconstruct the original documents. We present a novel unsupervised generative semantic hashing approach, \textit{Ranking based Semantic Hashing} (RBSH) that consists of both a variational and a ranking based component. Similarly to variational autoencoders, the variational component is trai…
A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows. The neural IR community made great advancements in training effective dual-encoder dense retrieval (DR) models recently. A dense text retrieval model uses a single vector representation per query and passage to score a match, which enables low-latency first stage retrieval with a nearest neighbor search. Increasingly common, training approaches require enormous compute power, as they either conduct negative passage sampling out of a continu…
University of Amsterdam（阿姆斯特丹大学）；University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Google Research（谷歌研究院）
Despite the impressive improvements achieved by unsupervised deep neural networks in computer vision and NLP tasks, such improvements have not yet been observed in ranking for information retrieval. The reason may be the complexity of the ranking problem, as it is not obvious how to learn from queries and documents when no supervised signal is available. Hence, in this paper, we propose to train a neural ranking model using weak supervision, where labels are obtained automatically without human annotators or any external resources (e.g., click data). To this aim, we use the output of an unsupe…
