Evaluating Large Language Models for Cross-Lingual Retrieval

• URL: http://arxiv.org/abs/2509.14749v1
• Date: Thu, 18 Sep 2025 08:54:17 GMT
• Title: Evaluating Large Language Models for Cross-Lingual Retrieval
• Authors: Longfei Zuo, Pingjun Hong, Oliver Kraus, Barbara Plank, Robert Litschko,
• Abstract summary: We study the interaction between retrievers and rerankers in two-stage CLIR with Large Language Models (LLMs)<n>Our findings reveal that, without machine translation, current state-of-the-art rerankers fall severely short when directly applied in CLIR.
• Score: 30.491003480391328
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-stage information retrieval (IR) has become a widely-adopted paradigm in search. While Large Language Models (LLMs) have been extensively evaluated as second-stage reranking models for monolingual IR, a systematic large-scale comparison is still lacking for cross-lingual IR (CLIR). Moreover, while prior work shows that LLM-based rerankers improve CLIR performance, their evaluation setup relies on lexical retrieval with machine translation (MT) for the first stage. This is not only prohibitively expensive but also prone to error propagation across stages. Our evaluation on passage-level and document-level CLIR reveals that further gains can be achieved with multilingual bi-encoders as first-stage retrievers and that the benefits of translation diminishes with stronger reranking models. We further show that pairwise rerankers based on instruction-tuned LLMs perform competitively with listwise rerankers. To the best of our knowledge, we are the first to study the interaction between retrievers and rerankers in two-stage CLIR with LLMs. Our findings reveal that, without MT, current state-of-the-art rerankers fall severely short when directly applied in CLIR.

Related papers

• Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From [73.76577052090695]
  We evaluate the cross-lingual context retrieval of over 40 large language models (LLMs) across 12 languages.<n>Post-trained open LLMs show strong cross-lingual context retrieval ability, comparable to closed-source LLMs.<n>Our results indicate that larger-scale pretraining cannot improve the xMRC performance.
  arXiv  Detail & Related papers  (2025-04-15T06:35:27Z)
• U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack [9.760456105567078]
  This paper introduces U-NIAH, a unified framework that systematically compares Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG)<n>Our framework incorporates multi-needle, long-needle, and needle-in-needle configurations, along with different retrieval settings.<n>Our findings show that RAG significantly enhances smaller LLMs by mitigating the "lost-in-the-middle" effect and improving robustness.
  arXiv  Detail & Related papers  (2025-03-01T05:05:24Z)
• Eliciting In-context Retrieval and Reasoning for Long-context Large Language Models [27.217391392240113]
  Long-context language models (LCLMs) can process entire knowledge bases and perform retrieval and reasoning directly.<n>Existing benchmarks like LOFT often overestimate LCLM performance by providing overly simplified contexts.<n>We introduce ICR2, a benchmark that evaluates LCLMs in more realistic scenarios by including confounding passages retrieved with strong retrievers.<n>We then propose three methods to enhance LCLM performance: (1) retrieve-then-generate fine-tuning, (2) retrieval-attention-probing, which uses attention heads to filter and de-noise long contexts during decoding, and (3) joint retrieval head training alongside the generation head.
  arXiv  Detail & Related papers  (2025-01-14T16:38:33Z)
• An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
  FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token. We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains. Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
  arXiv  Detail & Related papers  (2024-11-08T12:08:17Z)
• FIRST: Faster Improved Listwise Reranking with Single Token Decoding [56.727761901751194]
  First, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
  arXiv  Detail & Related papers  (2024-06-21T21:27:50Z)
• TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement [26.26493253161022]
  Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT) We introduce a systematic LLM-based self-refinement translation framework, named textbfTEaR.
  arXiv  Detail & Related papers  (2024-02-26T07:58:12Z)
• "Knowing When You Don't Know": A Multilingual Relevance Assessment Dataset for Robust Retrieval-Augmented Generation [90.09260023184932]
  Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) output by leveraging external knowledge sources to reduce factual hallucinations. NoMIRACL is a human-annotated dataset for evaluating LLM robustness in RAG across 18 typologically diverse languages. We measure relevance assessment using: (i) hallucination rate, measuring model tendency to hallucinate, when the answer is not present in passages in the non-relevant subset, and (ii) error rate, measuring model inaccuracy to recognize relevant passages in the relevant subset.
  arXiv  Detail & Related papers  (2023-12-18T17:18:04Z)
• Benchmarking Large Language Models in Retrieval-Augmented Generation [53.504471079548]
  We systematically investigate the impact of Retrieval-Augmented Generation on large language models. We analyze the performance of different large language models in 4 fundamental abilities required for RAG. We establish Retrieval-Augmented Generation Benchmark (RGB), a new corpus for RAG evaluation in both English and Chinese.
  arXiv  Detail & Related papers  (2023-09-04T08:28:44Z)
• 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)
• Learning Cross-Lingual IR from an English Retriever [10.27108918912692]
  The proposed model is far more effective than the existing approach of fine-tuning with cross-lingual labeled IR data, with a gain in accuracy of 25.4 Recall@5kt.
  arXiv  Detail & Related papers  (2021-12-15T15:07:54Z)

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.