Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, yet it still falters when answers must be pieced together across semantically distant documents. We close this gap with the Hierarchical Lexical Graph (HLG), a three-tier index that (i) traces every atomic proposition to its source, (ii) clusters propositions into latent topics, and (iii) links entities and relations to expose cross-document paths. On top of HLG we build two complementary, plug-and-play retrievers: StatementGraphRAG, which performs fine-grained entity-aware beam search over propositions for high-precision factoid questions, and TopicGraphRAG, which selects coarse topics before expanding along entity links to supply broad yet relevant context for exploratory queries. Additionally, existing benchmarks lack the complexity required to rigorously evaluate multi-hop summarization systems, often focusing on single-document queries or limited datasets. To address this, we introduce a synthetic dataset generation pipeline that curates realistic, multi-document question-answer pairs, enabling robust evaluation of multi-hop retrieval systems. Extensive experiments across five datasets demonstrate that our methods outperform naive chunk-based RAG achieving an average relative improvement of 23.1% in retrieval recall and correctness. Open-source Python library is available at https://github.com/awslabs/graphrag-toolkit.
Language Technologies Institute（语言技术研究所）；Carnegie Mellon University（卡内基梅隆大学）
Classical information retrieval systems such as BM25 rely on exact lexical match and carry out search efficiently with inverted list index. Recent neural IR models shifts towards soft semantic matching all query document terms, but they lose the computation efficiency of exact match systems. This paper presents COIL, a contextualized exact match retrieval architecture that brings semantic lexical matching. COIL scoring is based on overlapping query document tokens' contextualized representations. The new architecture stores contextualized token representations in inverted lists, bringing toget…
Neural Information Retrieval models hold the promise to replace lexical matching models, e.g. BM25, in modern search engines. While their capabilities have fully shone on in-domain datasets like MS MARCO, they have recently been challenged on out-of-domain zero-shot settings (BEIR benchmark), questioning their actual generalization capabilities compared to bag-of-words approaches. Particularly, we wonder if these shortcomings could (partly) be the consequence of the inability of neural IR models to perform lexical matching off-the-shelf. In this work, we propose a measure of discrepancy betwee…
In neural Information Retrieval (IR), 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 \emph{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. Introduced recently, the SPLADE model provides highly sparse representations and comp…
David R. Cheriton School of Computer Science（大卫·R·切里顿计算机科学学院）；University of Waterloo（滑铁卢大学）
Sparse lexical representation learning has demonstrated much progress in improving passage retrieval effectiveness in recent models such as DeepImpact, uniCOIL, and SPLADE. This paper describes a straightforward yet effective approach for sparsifying lexical representations for passage retrieval, building on SPLADE by introducing a top-$k$ masking scheme to control sparsity and a self-learning method to coax masked representations to mimic unmasked representations. A basic implementation of our model is competitive with more sophisticated approaches and achieves a good balance between effectiv…
Bosch Center for Artificial Intelligence（博世人工智能中心）；Carnegie Mellon University（卡内基梅隆大学）
We study the utility of the lexical translation model (IBM Model 1) for English text retrieval, in particular, its neural variants that are trained end-to-end. We use the neural Model1 as an aggregator layer applied to context-free or contextualized query/document embeddings. This new approach to design a neural ranking system has benefits for effectiveness, efficiency, and interpretability. Specifically, we show that adding an interpretable neural Model 1 layer on top of BERT-based contextualized embeddings (1) does not decrease accuracy and/or efficiency; and (2) may overcome the limitation …
Japan Advanced Institute of Science and Technology（日本先进科学技术研究院）；National Institute of Informatics（国立信息学研究所）
We present our method for tackling the legal case retrieval task of the Competition on Legal Information Extraction/Entailment 2019. Our approach is based on the idea that summarization is important for retrieval. On one hand, we adopt a summarization based model called encoded summarization which encodes a given document into continuous vector space which embeds the summary properties of the document. We utilize the resource of COLIEE 2018 on which we train the document representation model. On the other hand, we extract lexical features on different parts of a given query and its candidates.…
Indian Institute of Technology, Kanpur（印度理工学院坎普尔分校）；Vellore Institute of Technology（韦洛尔理工学院）
This paper describes our submission to the Competition on Legal Information Extraction/Entailment 2022 (COLIEE-2022) workshop on case law competition for tasks 1 and 2. Task 1 is a legal case retrieval task, which involves reading a new case and extracting supporting cases from the provided case law corpus to support the decision. Task 2 is the legal case entailment task, which involves the identification of a paragraph from existing cases that entails the decision in a relevant case. We employed the neural models Sentence-BERT and Sent2Vec for semantic understanding and the traditional retrie…
The terminology used in Biomedicine shows lexical peculiarities that have required the elaboration of terminological resources and information retrieval systems with specific functionalities. The main characteristics are the high rates of synonymy and homonymy, due to phenomena such as the proliferation of polysemic acronyms and their interaction with common language. Information retrieval systems in the biomedical domain use techniques oriented to the treatment of these lexical peculiarities. In this paper we review some of the techniques used in this domain, such as the application of Natura…
1-800-SHARED-TASKS at RegNLP: Lexical Reranking of Semantic Retrieval (LeSeR) for Regulatory Question Answering
Pulchowk Campus, IoE（伊奥学院普尔乔克校区）；Cohere For AI Community（Cohere AI社区）；IIT Roorkee（鲁基印度理工学院）；NUST（巴基斯坦国家科技大学）；University of Wisconsin（威斯康星大学）；University of Maryland（马里兰大学）
Tokenization is a crucial step in information retrieval, especially for lexical matching algorithms, where the quality of indexable tokens directly impacts the effectiveness of a retrieval system. Since different languages have unique properties, the design of the tokenization algorithm is usually language-specific and requires at least some lingustic knowledge. However, only a handful of the 7000+ languages on the planet benefit from specialized, custom-built tokenization algorithms, while the other languages are stuck with a "default" whitespace tokenizer, which cannot capture the intricacie…
Language Model Re-rankers are Fooled by Lexical Similarities
Chalmers University of Technology（楚德大学）；University of Gothenburg（哥德堡大学）；LMU Munich（慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；amass technologies（amass技术公司）
University of Maryland（马里兰大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
The advent of transformer-based models such as BERT has led to the rise of neural ranking models. These models have improved the effectiveness of retrieval systems well beyond that of lexical term matching models such as BM25. While monolingual retrieval tasks have benefited from large-scale training collections such as MS MARCO and advances in neural architectures, cross-language retrieval tasks have fallen behind these advancements. This paper introduces ColBERT-X, a generalization of the ColBERT multi-representation dense retrieval model that uses the XLM-RoBERTa (XLM-R) encoder to support …
HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
Peking University（北京大学）；Center for LLM, Institute for Advanced Algorithms Research（大模型中心，高级算法研究所）；Huazhong University of Science and Technology（华中科技大学）
Mouloud Mammeri University of Tizi-Ouzou（穆卢德·马姆里蒂齐乌祖大学）
Traditional information retrieval systems rely on keywords to index documents and queries. In such systems, documents are retrieved based on the number of shared keywords with the query. This lexical-focused retrieval leads to inaccurate and incomplete results when different keywords are used to describe the documents and queries. Semantic-focused retrieval approaches attempt to overcome this problem by relying on concepts rather than on keywords to indexing and retrieval. The goal is to retrieve documents that are semantically relevant to a given user query. This paper addresses this issue by…
Multi-hop reasoning (i.e., reasoning across two or more documents) is a key ingredient for NLP models that leverage large corpora to exhibit broad knowledge. To retrieve evidence passages, multi-hop models must contend with a fast-growing search space across the hops, represent complex queries that combine multiple information needs, and resolve ambiguity about the best order in which to hop between training passages. We tackle these problems via Baleen, a system that improves the accuracy of multi-hop retrieval while learning robustly from weak training signals in the many-hop setting. To tam…
Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for information-seeking scenarios, users often provide information on whether a document is relevant to their query in form of clicks or explicit feedback. Therefore, in this work, we explore how relevance feedback can be directly integrated into neural re-ranking models by adopting few-shot and parameter-efficient learning techniques. Specifically, we introduce a k…
We propose the Neural Vector Space Model (NVSM), a method that learns representations of documents in an unsupervised manner for news article retrieval. In the NVSM paradigm, we learn low-dimensional representations of words and documents from scratch using gradient descent and rank documents according to their similarity with query representations that are composed from word representations. We show that NVSM performs better at document ranking than existing latent semantic vector space methods. The addition of NVSM to a mixture of lexical language models and a state-of-the-art baseline vecto…
Technion – Israel Institute of Technology（以色列理工学院）
This paper is concerned with the task of multi-hop open-domain Question Answering (QA). This task is particularly challenging since it requires the simultaneous performance of textual reasoning and efficient searching. We present a method for retrieving multiple supporting paragraphs, nested amidst a large knowledge base, which contain the necessary evidence to answer a given question. Our method iteratively retrieves supporting paragraphs by forming a joint vector representation of both a question and a paragraph. The retrieval is performed by considering contextualized sentence-level represe…
LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data. It has been argued that this is an inherent limitation of dense models. We rebut this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. We show that a dense Lexical Model Λ can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retrieve…
Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation
Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China（长江三角洲地区研究院（湖州），电子科学与技术大学）；School of Information and Software Engineering, University of Electronic Science and Technology of China（信息与软件工程学院，电子科学与技术大学）
HCMC University of Technology（胡志明市理工大学）；John von Neumann Institute（约翰·冯·诺依曼研究所）
Text search based on lexical matching of keywords is not satisfactory due to polysemous and synonymous words. Semantic search that exploits word meanings, in general, improves search performance. In this paper, we survey WordNet-based information retrieval systems, which employ a word sense disambiguation method to process queries and documents. The problem is that in many cases a word has more than one possible direct sense, and picking only one of them may give a wrong sense for the word. Moreover, the previous systems use only word forms to represent word senses and their hypernyms. We prop…
Japan Advanced Institute of Science and Technology (JAIST)（日本先端科学技术大学院大学）；Hung Yen University of Education and Technology (UTEHY)（兴安教育技术大学）
In the context of the Competition on Legal Information Extraction/Entailment (COLIEE), we propose a method comprising the necessary steps for finding relevant documents to a legal question and deciding on textual entailment evidence to provide a correct answer. The proposed method is based on the combination of several lexical and morphological characteristics, to build a language model and a set of features for Machine Learning algorithms. We provide a detailed study on the proposed method performance and failure cases, indicating that it is competitive with state-of-the-art approaches on Leg…
Key Laboratory of Computational Linguistics, Peking University, MOE（北京大学计算语言学重点实验室（教育部））
Question retrieval is a crucial subtask for community question answering. Previous research focus on supervised models which depend heavily on training data and manual feature engineering. In this paper, we propose a novel unsupervised framework, namely reduced attentive matching network (RAMN), to compute semantic matching between two questions. Our RAMN integrates together the deep semantic representations, the shallow lexical mismatching information and the initial rank produced by an external search engine. For the first time, we propose attention autoencoders to generate semantic represen…
Evidence retrieval is a critical stage of question answering (QA), necessary not only to improve performance, but also to explain the decisions of the corresponding QA method. We introduce a simple, fast, and unsupervised iterative evidence retrieval method, which relies on three ideas: (a) an unsupervised alignment approach to soft-align questions and answers with justification sentences using only GloVe embeddings, (b) an iterative process that reformulates queries focusing on terms that are not covered by existing justifications, which (c) a stopping criterion that terminates retrieval when…
