BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation

• URL: http://arxiv.org/abs/2410.01171v1
• Date: Wed, 2 Oct 2024 01:59:07 GMT
• Title: BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation
• Authors: Bryan Li, Samar Haider, Fiona Luo, Adwait Agashe, Chris Callison-Burch,
• Abstract summary: We study the challenge of cross-lingual RAG and present a dataset to investigate the robustness of existing systems. Our results show that existing RAG systems continue to be challenged by cross-lingual use cases and suffer from a lack of consistency when they are provided with competing information in multiple languages.
• Score: 34.650355693901034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models excel at creative generation but continue to struggle with the issues of hallucination and bias. While retrieval-augmented generation (RAG) provides a framework for grounding LLMs' responses in accurate and up-to-date information, it still raises the question of bias: which sources should be selected for inclusion in the context? And how should their importance be weighted? In this paper, we study the challenge of cross-lingual RAG and present a dataset to investigate the robustness of existing systems at answering queries about geopolitical disputes, which exist at the intersection of linguistic, cultural, and political boundaries. Our dataset is sourced from Wikipedia pages containing information relevant to the given queries and we investigate the impact of including additional context, as well as the composition of this context in terms of language and source, on an LLM's response. Our results show that existing RAG systems continue to be challenged by cross-lingual use cases and suffer from a lack of consistency when they are provided with competing information in multiple languages. We present case studies to illustrate these issues and outline steps for future research to address these challenges. We make our dataset and code publicly available at https://github.com/manestay/bordIRlines.

Related papers

• Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task [73.35882908048423]
  Retrieval-augmented generation (RAG) has become a cornerstone of contemporary NLP. This paper investigates the effectiveness of RAG across multiple languages by proposing novel approaches for multilingual open-domain question-answering.
  arXiv  Detail & Related papers  (2025-04-04T17:35:43Z)
• Not All Languages are Equal: Insights into Multilingual Retrieval-Augmented Generation [38.631934251052485]
  We evaluate six multilingual RALMs using our benchmark to explore the challenges of multilingual RALMs. High-resource languages stand out in Monolingual Knowledge Extraction. Indo-European languages lead RALMs to provide answers directly from documents. English benefits from RALMs' selection bias and speaks louder in multilingual knowledge selection.
  arXiv  Detail & Related papers  (2024-10-29T11:53:19Z)
• Crosslingual Capabilities and Knowledge Barriers in Multilingual Large Language Models [62.91524967852552]
  Large language models (LLMs) are typically multilingual due to pretraining on diverse multilingual corpora. But can these models relate corresponding concepts across languages, i.e., be crosslingual? This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Integrating Large Language Models with Graph-based Reasoning for Conversational Question Answering [58.17090503446995]
  We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our method utilizes a graph structured representation to aggregate information about a question and its context.
  arXiv  Detail & Related papers  (2024-06-14T13:28:03Z)
• What Evidence Do Language Models Find Convincing? [94.90663008214918]
  We build a dataset that pairs controversial queries with a series of real-world evidence documents that contain different facts. We use this dataset to perform sensitivity and counterfactual analyses to explore which text features most affect LLM predictions. Overall, we find that current models rely heavily on the relevance of a website to the query, while largely ignoring stylistic features that humans find important.
  arXiv  Detail & Related papers  (2024-02-19T02:15:34Z)
• Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval [62.82448161570428]
  This dataset is designed to investigate fairness in a multilingual information retrieval context. It boasts an authentic multilingual corpus, featuring topics translated into all 24 languages. It offers rich demographic information associated with its documents, facilitating the study of demographic bias.
  arXiv  Detail & Related papers  (2023-11-03T12:29:11Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Breaking Language Barriers with MMTweets: Advancing Cross-Lingual Debunked Narrative Retrieval for Fact-Checking [5.880794128275313]
  Cross-lingual debunked narrative retrieval is an understudied problem. This study introduces cross-lingual debunked narrative retrieval and addresses this research gap by: (i) creating Multilingual Misinformation Tweets (MMTweets) MMTweets features cross-lingual pairs, images, human annotations, and fine-grained labels, making it a comprehensive resource compared to its counterparts. We find that MMTweets presents challenges for cross-lingual debunked narrative retrieval, highlighting areas for improvement in retrieval models.
  arXiv  Detail & Related papers  (2023-08-10T16:33:17Z)
• Evaluating and Modeling Attribution for Cross-Lingual Question Answering [80.4807682093432]
  This work is the first to study attribution for cross-lingual question answering. We collect data in 5 languages to assess the attribution level of a state-of-the-art cross-lingual QA system. We find that a substantial portion of the answers is not attributable to any retrieved passages.
  arXiv  Detail & Related papers  (2023-05-23T17:57:46Z)
• Soft Prompt Decoding for Multilingual Dense Retrieval [30.766917713997355]
  We show that applying state-of-the-art approaches developed for cross-lingual information retrieval to MLIR tasks leads to sub-optimal performance. This is due to the heterogeneous and imbalanced nature of multilingual collections. We present KD-SPD, a novel soft prompt decoding approach for MLIR that implicitly "translates" the representation of documents in different languages into the same embedding space.
  arXiv  Detail & Related papers  (2023-05-15T21:17:17Z)
• PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale [53.92008514395125]
  PAXQA (Projecting annotations for cross-lingual (x) QA) decomposes cross-lingual QA into two stages. We propose a novel use of lexically-constrained machine translation, in which constrained entities are extracted from the parallel bitexts. We show that models fine-tuned on these datasets outperform prior synthetic data generation models over several extractive QA datasets.
  arXiv  Detail & Related papers  (2023-04-24T15:46:26Z)
• ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System [16.89747171947662]
  This paper introduces our proposed system for the MIA Shared Task on Cross-lingual Open-retrieval Question Answering (COQA) In this challenging scenario, given an input question the system has to gather evidence documents from a multilingual pool and generate an answer in the language of the question. We devised several approaches combining different model variants for three main components: Data Augmentation, Passage Retrieval, and Answer Generation.
  arXiv  Detail & Related papers  (2022-05-30T10:31:08Z)
• A Survey on non-English Question Answering Dataset [0.0]
  The aim of this survey is to recognize, summarize and analyze the existing datasets that have been released by many researchers. In this paper, we review question answering datasets that are available in common languages other than English such as French, German, Japanese, Chinese, Arabic, Russian, as well as the multilingual and cross-lingual question-answering datasets.
  arXiv  Detail & Related papers  (2021-12-27T12:45:06Z)
• On Cross-Lingual Retrieval with Multilingual Text Encoders [51.60862829942932]
  We study the suitability of state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks. We benchmark their performance in unsupervised ad-hoc sentence- and document-level CLIR experiments. We evaluate multilingual encoders fine-tuned in a supervised fashion (i.e., we learn to rank) on English relevance data in a series of zero-shot language and domain transfer CLIR experiments.
  arXiv  Detail & Related papers  (2021-12-21T08:10:27Z)
• Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets [26.486492641924226]
  This study examines selected toxic text datasets with the goal of shedding light on some of the inherent issues. We re-annotate samples from three toxic text datasets and find that a multi-label approach to annotating toxic text samples can help to improve dataset quality.
  arXiv  Detail & Related papers  (2021-12-07T06:58:22Z)
• Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval [51.004601358498135]
  Mr. TyDi is a benchmark dataset for mono-lingual retrieval in eleven typologically diverse languages. The goal of this resource is to spur research in dense retrieval techniques in non-English languages.
  arXiv  Detail & Related papers  (2021-08-19T16:53:43Z)
• XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning [68.57658225995966]
  Cross-lingual Choice of Plausible Alternatives (XCOPA) is a typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages. We evaluate a range of state-of-the-art models on this novel dataset, revealing that the performance of current methods falls short compared to translation-based transfer.
  arXiv  Detail & Related papers  (2020-05-01T12:22:33Z)
• LAReQA: Language-agnostic answer retrieval from a multilingual pool [29.553907688813347]
  LAReQA tests for "strong" cross-lingual alignment. We find that augmenting training data via machine translation is effective. This finding underscores our claim that languageagnostic retrieval is a substantively new kind of cross-lingual evaluation.
  arXiv  Detail & Related papers  (2020-04-11T20:51:11Z)

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.