LAMAR: An Open Language-Aware Multilingual Alignment Reranker

• URL: http://arxiv.org/abs/2607.22042v2
• Date: Tue, 28 Jul 2026 16:54:28 GMT
• Title: LAMAR: An Open Language-Aware Multilingual Alignment Reranker
• Abstract summary: We show that multilingual rerankers do not consistently prioritize documents written in the same language as the query.<n>We release LAMAR, a language aware multilingual cross encoder trained to account for both semantic relevance and language coherence.
• Score: 24.064060212702838
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In multilingual retrieval augmented generation pipelines, an embedding model can retrieve relevant documents written in multiple languages, which are subsequently reranked before answer generation. However, it remains unclear whether existing multilingual rerankers consider document language when ordering semantically relevant candidates. Our analysis shows that these rerankers do not consistently prioritize documents written in the same language as the query when semantically equivalent documents are available across languages, even though document language can affect answer generation. We release LAMAR, a language aware multilingual cross encoder trained to account for both semantic relevance and language coherence. LAMAR first uses English anchored relevance distillation to establish consistent relevance scoring across multilingual inputs and then applies preference alignment for language coherence to encourage documents written in the same language as the query to receive higher rankings while retaining semantic relevance. In a controlled experiment designed to assess language coherence, LAMAR achieves the best performance overall and across all languages examined individually. LAMAR also remains competitive on established multilingual reranking benchmarks. In practical retrieval settings, LAMAR achieves the best results across all reported metrics when reranking candidates retrieved in the first stage. These results demonstrate that LAMAR accounts for language coherence while achieving strong performance on general multilingual reranking benchmarks.

Related papers

• SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval [26.186599286240362]
  Multilingual Information Retrieval (MLIR) has emerged as a critical technology for global information access.<n>Recent multilingual dense retrieval models often exhibit a strong preference for documents in the same language as the query.<n>We propose SHIFT, a training-free method applicable in the indexing stage.
  arXiv  Detail & Related papers  (2026-06-17T08:14:51Z)
• MLAIRE: Multilingual Language-Aware Information Retrieval Evaluation Protocal [26.186599286240362]
  MLAIRE is a Multilingual Language-Aware Information Retrieval Evaluation protocol.<n>It disentangles cross-lingual semantic retrieval from query-language preference.<n>We show that standard metrics obscure distinct behaviors.
  arXiv  Detail & Related papers  (2026-05-08T05:10:05Z)
• The Cross-Lingual Cost: Retrieval Biases in RAG over Arabic-English Corpora [5.0908395672023055]
  Cross-lingual retrieval-augmented generation (RAG) is a critical capability for retrieving and generating answers across languages.<n>We study Arabic-English RAG in a domain-specific setting using benchmarks derived from real-world corporate datasets.<n>We propose two simple retrieval strategies that address this source of failure by enforcing equal retrieval from both languages or by translating the query.
  arXiv  Detail & Related papers  (2025-07-10T08:38:31Z)
• mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval [61.17793165194077]
  We introduce mFollowIR, a benchmark for measuring instruction-following ability in retrieval models.<n>We present results for both multilingual (XX-XX) and cross-lingual (En-XX) performance.<n>We see strong cross-lingual performance with English-based retrievers that trained using instructions, but find a notable drop in performance in the multilingual setting.
  arXiv  Detail & Related papers  (2025-01-31T16:24:46Z)
• Language Fairness in Multilingual Information Retrieval [9.358582006140903]
  This work proposes a language fairness metric to evaluate whether documents across different languages are fairly ranked. In contrast to most prior work in group fairness, we do not consider any language to be an unprotected group. Our proposed measure, PEER, is the first fairness metric specifically designed to capture the language fairness of MLIR systems.
  arXiv  Detail & Related papers  (2024-05-02T03:30:15Z)
• Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval [80.43859162884353]
  We propose a multilingual multilingual language model called masked sentence model (MSM)<n>MSM consists of a sentence encoder to generate the sentence representations, and a document encoder applied to a sequence of sentence vectors from a document.<n>To train the model, we propose a masked sentence prediction task, which masks and predicts the sentence vector via a hierarchical contrastive loss with sampled negatives.
  arXiv  Detail & Related papers  (2023-02-03T09:54:27Z)
• Advancing Multilingual Pre-training: TRIP Triangular Document-level Pre-training for Multilingual Language Models [107.83158521848372]
  We present textbfTriangular Document-level textbfPre-training (textbfTRIP), which is the first in the field to accelerate the conventional monolingual and bilingual objectives into a trilingual objective with a novel method called Grafting. TRIP achieves several strong state-of-the-art (SOTA) scores on three multilingual document-level machine translation benchmarks and one cross-lingual abstractive summarization benchmark, including consistent improvements by up to 3.11 d-BLEU points and 8.9 ROUGE-L points.
  arXiv  Detail & Related papers  (2022-12-15T12:14:25Z)
• 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)
• FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding [85.29270319872597]
  We propose an enhanced fusion method that takes cross-lingual data as input for XLM finetuning. During inference, the model makes predictions based on the text input in the target language and its translation in the source language. To tackle this issue, we propose an additional KL-divergence self-teaching loss for model training, based on auto-generated soft pseudo-labels for translated text in the target language.
  arXiv  Detail & Related papers  (2020-09-10T22:42:15Z)
• XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization [128.37244072182506]
  Cross-lingual TRansfer Evaluation of Multilinguals XTREME is a benchmark for evaluating the cross-lingual generalization capabilities of multilingual representations across 40 languages and 9 tasks. We demonstrate that while models tested on English reach human performance on many tasks, there is still a sizable gap in the performance of cross-lingually transferred models.
  arXiv  Detail & Related papers  (2020-03-24T19:09:37Z)

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.