Retrieval-augmented generation (RAG) with large language models (LLMs) has demonstrated strong performance in multilingual question-answering (QA) tasks by leveraging relevant passages retrieved from corpora. In multilingual RAG (mRAG), the retrieved passages can be written in languages other than that of the query entered by the user, making it challenging for LLMs to effectively utilize the provided information. Recent research suggests that retrieving passages from multilingual corpora can improve RAG performance, particularly for low-resource languages. However, the extent to which LLMs can leverage different kinds of multilingual contexts to generate accurate answers, independently from retrieval quality, remains understudied. In this paper, we conduct an extensive assessment of LLMs’ ability to (i) make consistent use of a relevant passage regardless of its language, (ii) respond in the expected language, and (iii) focus on the relevant passage even when multiple ‘distracting passages’ in different languages are provided in the context. Our experiments with four LLMs across three QA datasets covering 48 languages reveal a surprising ability of LLMs to extract relevant information from passages in a different language than the query, but a much weaker ability to produce a full answer in the correct language. Our analysis, based on both accuracy and feature attribution techniques, further shows that distracting passages negatively impact answer quality regardless of their language. However, distractors in the query language exert a slightly stronger influence. Taken together, our findings deepen the understanding of how LLMs utilize context in mRAG systems, providing directions for future improvements. All codes and data are released at https://github.com/Betswish/mRAG-Context-Consistency.

Recent work suggests that large language models enhanced with retrieval-augmented generation are easily influenced by the order in which the retrieved documents are presented to the model when solving tasks such as question answering (QA).However, there is no method to date that exploits this phenomenon to improve generation.To fill this gap, in this study, we show that the pointwise mutual information between a context and a question is an effective gauge for language model performance.Importantly, this gauge does not depend on knowing the answer to the question a priori.Through experiments on two question-answering datasets using a variety of large language models, we find evidence for an empirical correlation between answer accuracy and pointwise mutual information.Additionally, we propose two methods that use the pointwise mutual information between a document and a question as a gauge for selecting and constructing prompts that lead to better performance, whose effectiveness we demonstrate through experimentation.

Ensuring the verifiability of model answers is a fundamental challenge for retrieval-augmented generation (RAG) in the question answering (QA) domain. Recently, self-citation prompting was proposed to make large language models (LLMs) generate citations to supporting documents along with their answers. However, self-citing LLMs often struggle to match the required format, refer to non-existent sources, and fail to faithfully reflect LLMs’ context usage throughout the generation. In this work, we present MIRAGE – Model Internals-based RAG Explanations – a plug-and-play approach using model internals for faithful answer attribution in RAG applications. MIRAGE detects context-sensitive answer tokens and pairs them with retrieved documents contributing to their prediction via saliency methods. We evaluate our proposed approach on a multilingual extractive QA dataset, finding high agreement with human answer attribution. On open-ended QA, MIRAGE achieves citation quality and efficiency comparable to self-citation while also allowing for a finer-grained control of attribution parameters. Our qualitative evaluation highlights the faithfulness of MIRAGE’s attributions and underscores the promising application of model internals for RAG answer attribution. Code and data released at https://github.com/Betswish/MIRAGE.

Following multiple instructions is a crucial ability for large language models (LLMs). Evaluating this ability comes with significant challenges: (i) limited coherence between multiple instructions, (ii) positional bias where the order of instructions affects model performance, and (iii) a lack of objectively verifiable tasks. To address these issues, we introduce a benchmark designed to evaluate models’ abilities to follow multiple instructions through sequential instruction following (SIFo) tasks. In SIFo, the successful completion of multiple instructions is verifiable by examining only the final instruction. Our benchmark evaluates instruction following using four tasks (text modification, question answering, mathematics, and security rule following), each assessing different aspects of sequential instruction following. Our evaluation of popular LLMs, both closed-source and open-source, shows that more recent and larger models significantly outperform their older and smaller counterparts on the SIFo tasks, validating the benchmark’s effectiveness. All models struggle with following sequences of instructions, hinting at an important lack of robustness of today’s language models.

Multilingual large-scale Pretrained Language Models (PLMs) have been shown to store considerable amounts of factual knowledge, but large variations are observed across languages. With the ultimate goal of ensuring that users with different language backgrounds obtain consistent feedback from the same model, we study the cross-lingual consistency (CLC) of factual knowledge in various multilingual PLMs. To this end, we propose a Ranking-based Consistency (RankC) metric to evaluate knowledge consistency across languages independently from accuracy. Using this metric, we conduct an in-depth analysis of the determining factors for CLC, both at model level and at language-pair level. Among other results, we find that increasing model size leads to higher factual probing accuracy in most languages, but does not improve cross-lingual consistency. Finally, we conduct a case study on CLC when new factual associations are inserted in the PLMs via model editing. Results on a small sample of facts inserted in English reveal a clear pattern whereby the new piece of knowledge transfers only to languages with which English has a high RankC score. All code and data are released at https://github.com/Betswish/Cross-Lingual-Consistency.

Prompt-based learning has achieved excellent performance in few-shot learning by mapping the outputs of the pre-trained language model to the labels with the help of a label mapping component. Existing manual label mapping (MLM) methods achieve good results but heavily rely on expensive human knowledge. Automatic label mapping (ALM) methods that learn the mapping functions with extra parameters have shown their potentiality. However, no effective ALM model comparable to MLM methods is developed yet due to the limited data. In this paper, we propose a Latent Pseudo Label Mapping (LPLM) method that optimizes the label mapping without human knowledge and extra parameters. LPLM is built upon a probabilistic latent model and is iteratively self-improved with the EM-style algorithm. The empirical results demonstrate that our LPLM method is superior to the mainstream ALM methods and significantly outperforms the SOTA method in few-shot classification tasks. Moreover, LPLM also shows impressively better performance than the vanilla MLM method which requires extra task-specific prior knowledge.