Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks

• URL: http://arxiv.org/abs/2504.12845v1
• Date: Thu, 17 Apr 2025 11:02:35 GMT
• Title: Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks
• Authors: Amey Hengle, Prasoon Bajpai, Soham Dan, Tanmoy Chakraborty,
• Abstract summary: MLRBench is a synthetic benchmark for multilingual long-context reasoning.<n>It is designed to be parallel, resistant to leakage, and scalable to arbitrary context lengths.
• Score: 22.859955360764275
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing multilingual long-context benchmarks, often based on the popular needle-in-a-haystack test, primarily evaluate a model's ability to locate specific information buried within irrelevant texts. However, such a retrieval-centric approach is myopic and inherently limited, as successful recall alone does not indicate a model's capacity to reason over extended contexts. Moreover, these benchmarks are susceptible to data leakage, short-circuiting, and risk making the evaluation a priori identifiable. To address these limitations, we introduce MLRBench, a new synthetic benchmark for multilingual long-context reasoning. Unlike existing benchmarks, MLRBench goes beyond surface-level retrieval by including tasks that assess multi-hop inference, aggregation, and epistemic reasoning. Spanning seven languages, MLRBench is designed to be parallel, resistant to leakage, and scalable to arbitrary context lengths. Our extensive experiments with an open-weight large language model (LLM) reveal a pronounced gap between high- and low-resource languages, particularly for tasks requiring the model to aggregate multiple facts or predict the absence of information. We also find that, in multilingual settings, LLMs effectively utilize less than 30% of their claimed context length. Although off-the-shelf Retrieval Augmented Generation helps alleviate this to a certain extent, it does not solve the long-context problem. We open-source MLRBench to enable future research in improved evaluation and training of multilingual LLMs.

Related papers

• Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From [61.63091726904068]
  We evaluate the cross-lingual context retrieval ability of over 40 large language models (LLMs) across 12 languages.<n>Several small, post-trained open LLMs show strong cross-lingual context retrieval ability.<n>Our results also indicate that larger-scale pretraining cannot improve the xMRC performance.
  arXiv  Detail & Related papers  (2025-04-15T06:35:27Z)
• Scaling Test-time Compute for Low-resource Languages: Multilingual Reasoning in LLMs [3.9530780161144667]
  We investigate the multilingual mechanism by which Large Language Models internally operate in a latent space biased toward their inherently dominant language.<n>We train models to generate the chain-of-thought (CoT) in English while outputting the final response in the target language, given input in the low-resource language.<n>Our experiments demonstrate that this approach, named English-Pivoted CoT Training, outperforms other baselines, with up to 28.33% improvement.
  arXiv  Detail & Related papers  (2025-04-02T16:58:36Z)
• On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generation [7.478369203246005]
  Retrieval-augmented generation (RAG) with large language models (LLMs) has demonstrated strong performance in multilingual question-answering tasks.<n>In multilingual RAG, retrieved passages can be written in languages other than that of the query entered by the user.
  arXiv  Detail & Related papers  (2025-04-01T09:55:23Z)
• Think Carefully and Check Again! Meta-Generation Unlocking LLMs for Low-Resource Cross-Lingual Summarization [108.6908427615402]
  Cross-lingual summarization ( CLS) aims to generate a summary for the source text in a different target language.<n>Currently, instruction-tuned large language models (LLMs) excel at various English tasks.<n>Recent studies have shown that LLMs' performance on CLS tasks remains unsatisfactory even with few-shot settings.
  arXiv  Detail & Related papers  (2024-10-26T00:39:44Z)
• Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models [22.859955360764275]
  We introduce the MultiLingual Needle-in-a-Haystack (MLNeedle) test to assess a model's ability to retrieve relevant information. We evaluate four state-of-the-art large language models on MLNeedle.
  arXiv  Detail & Related papers  (2024-08-19T17:02:06Z)
• Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
  We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts. We find that Llama Instruct and Mistral models exhibit high degrees of language confusion. We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
  arXiv  Detail & Related papers  (2024-06-28T17:03:51Z)
• Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA [71.04146366608904]
  Long-context modeling capabilities have garnered widespread attention, leading to the emergence of Large Language Models (LLMs) with ultra-context windows. We propose a novel long-context benchmark, Loong, aligning with realistic scenarios through extended multi-document question answering (QA) Loong introduces four types of tasks with a range of context lengths: Spotlight Locating, Comparison, Clustering, and Chain of Reasoning.
  arXiv  Detail & Related papers  (2024-06-25T09:42:56Z)
• 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.<n>But can these models relate corresponding concepts across languages, i.e., be crosslingual?<n>This study evaluates state-of-the-art LLMs on inherently crosslingual tasks.
  arXiv  Detail & Related papers  (2024-06-23T15:15:17Z)
• Are Large Language Models Really Robust to Word-Level Perturbations? [68.60618778027694]
  We propose a novel rational evaluation approach that leverages pre-trained reward models as diagnostic tools. Longer conversations manifest the comprehensive grasp of language models in terms of their proficiency in understanding questions. Our results demonstrate that LLMs frequently exhibit vulnerability to word-level perturbations that are commonplace in daily language usage.
  arXiv  Detail & Related papers  (2023-09-20T09:23:46Z)

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.