BERGEN: A Benchmarking Library for Retrieval-Augmented Generation

Retrieval-Augmented Generation allows to enhance Large Language Models with external knowledge. In response to the recent popularity of generative LLMs, many RAG approaches have been proposed, which involve an intricate number of different configurations such as evaluation datasets, collections, metrics, retrievers, and LLMs. Inconsistent benchmarking poses a major challenge in comparing approaches and understanding the impact of each component in the pipeline. In this work, we study best practices that lay the groundwork for a systematic evaluation of RAG and present BERGEN, an end-to-end library for reproducible research standardizing RAG experiments. In an extensive study focusing on QA, we benchmark different state-of-the-art retrievers, rerankers, and LLMs. Additionally, we analyze existing RAG metrics and datasets. Our open-source library BERGEN is available under \url{https://github.com/naver/bergen}.

Retrieval-augmented generation in multilingual settings

Retrieval-augmented generation (RAG) has recently emerged as a promising solution for incorporating up-to-date or domain-specific knowledge into large language models (LLMs) and improving LLM factuality, but is predominantly studied in English-only settings. In this work, we consider RAG in the multilingual setting (mRAG), i.e. with user queries and the datastore in 13 languages, and investigate which components and with which adjustments are needed to build a well-performing mRAG pipeline, that can be used as a strong baseline in future works. Our findings highlight that despite the availability of high-quality off-the-shelf multilingual retrievers and generators, task-specific prompt engineering is needed to enable generation in user languages. Moreover, current evaluation metrics need adjustments for multilingual setting, to account for variations in spelling named entities. The main limitations to be addressed in future works include frequent code-switching in non-Latin alphabet languages, occasional fluency errors, wrong reading of the provided documents, or irrelevant retrieval. We release the code for the resulting mRAG baseline pipeline at https://github.com/naver/bergen.

Investigating the potential of Sparse Mixtures-of-Experts for multi-domain neural machine translation

We focus on multi-domain Neural Machine Translation, with the goal of developing efficient models which can handle data from various domains seen during training and are robust to domains unseen during training. We hypothesize that Sparse Mixture-of-Experts (SMoE) models are a good fit for this task, as they enable efficient model scaling, which helps to accommodate a variety of multi-domain data, and allow flexible sharing of parameters between domains, potentially enabling knowledge transfer between similar domains and limiting negative transfer. We conduct a series of experiments aimed at validating the utility of SMoE for the multi-domain scenario, and find that a straightforward width scaling of Transformer is a simpler and surprisingly more efficient approach in practice, and reaches the same performance level as SMoE. We also search for a better recipe for robustness of multi-domain systems, highlighting the importance of mixing-in a generic domain, i.e. Paracrawl, and introducing a simple technique, domain randomization.

FrenchToxicityPrompts: a Large Benchmark for Evaluating and Mitigating Toxicity in French Texts

Large language models (LLMs) are increasingly popular but are also prone to generating bias, toxic or harmful language, which can have detrimental effects on individuals and communities. Although most efforts is put to assess and mitigate toxicity in generated content, it is primarily concentrated on English, while it's essential to consider other languages as well. For addressing this issue, we create and release FrenchToxicityPrompts, a dataset of 50K naturally occurring French prompts and their continuations, annotated with toxicity scores from a widely used toxicity classifier. We evaluate 14 different models from four prevalent open-sourced families of LLMs against our dataset to assess their potential toxicity across various dimensions. We hope that our contribution will foster future research on toxicity detection and mitigation beyond Englis

Zero-shot cross-lingual transfer in instruction tuning of large language model

Instruction tuning (IT) is widely used to teach pretrained large language models (LLMs) to follow arbitrary instructions, but is under-studied in multilingual settings. In this work, we conduct a systematic study of zero-shot cross-lingual transfer in IT, when an LLM is instruction-tuned on English-only data and then tested on user prompts in other languages. We investigate the influence of model configuration choices and devise a multi-facet evaluation strategy for multilingual instruction following. We find that cross-lingual transfer does happen successfully in IT even if all stages of model training are English-centric, but only if multiliguality is taken into account in hyperparameter tuning and with large enough IT data. English-trained LLMs are capable of generating correct-language, comprehensive and helpful responses in the other languages, but suffer from low factuality and may occasionally have fluency errors.

Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks

Zero-shot cross-lingual generation implies finetuning of the multilingual pretrained language model on a generation task in one language and then using it to make predictions for this task in other languages. Previous works notice a frequent problem of generation in a wrong language and propose approaches to address it, usually using mT5 as a backbone model. In this work we compare various approaches proposed from the literature in unified settings, also including alternative backbone models, namely mBART and NLLB-200. We first underline the importance of tuning learning rate used for finetuning, which helps to substantially alleviate the problem of generation in the wrong language. Then, we show that with careful learning rate tuning, the simple full finetuning of the model acts as a very strong baseline and alternative approaches bring only marginal improvements. Finally, we find that mBART performs similarly to mT5 of the same size, and NLLB-200 can be competitive in some cases. Our final models reach the performance of the approach based on data translation which is usually considered as an upper baseline for zero-shot cross-lingual generation.

DistilWhisper: Efficient Distillation of Multi-task Speech Models via Language-Specific Experts

Whisper is a multitask and multilingual speech model covering 99 languages. It yields commendable automatic speech recognition (ASR) results in a subset of its covered languages, but the model still under-performs on a non-negligible number of under-represented languages, a problem exacerbated in smaller model versions. In this work, we propose DistilWhisper, an approach able to bridge the performance gap in ASR for these languages while retaining the advantages of multitask and multilingual capabilities. Our approach involves two key strategies: lightweight modular ASR fine-tuning of whisper-small using language-specific experts, and knowledge distillation from whisper-large-v2. This dual approach allows us to effectively boost ASR performance while keeping the robustness inherited from the multitask and multilingual pre-training. Results demonstrate that our approach is more effective than standard fine-tuning or LoRA adapters, boosting performance in the targeted languages for both in- and out-of-domain test sets, while introducing only a negligible parameter overhead at inference.

Empirical study of pretrained multilingual language models for zero-shot cross-lingual generation

Zero-shot cross-lingual generation assumes finetuning the multilingual pretrained language model (mPLM) on a generation task in one language and then using it to make predictions for this task in other languages. Previous works notice a frequent problem of generation in a wrong language and propose approaches to address it, usually using mT5 as a backbone model. In this work, we test alternative mPLMs, such as mBART and NLLB, considering full finetuning and parameter-efficient finetuning with adapters. We find that mBART with adapters performs similarly to mT5 of the same size, and NLLB can be competitive in some cases. We also underline the importance of tuning learning rate used for finetuning, which helps to alleviate the problem of generation in the wrong language.

Long-Tail Theory under Gaussian Mixtures

We suggest a simple Gaussian mixture model for data generation that complies with Feldman's long tail theory (2020). We demonstrate that a linear classifier cannot decrease the generalization error below a certain level in the proposed model, whereas a nonlinear classifier with a memorization capacity can. This confirms that for long-tailed distributions, rare training examples must be considered for optimal generalization to new data. Finally, we show that the performance gap between linear and nonlinear models can be lessened as the tail becomes shorter in the subpopulation frequency distribution, as confirmed by experiments on synthetic and real data.

Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model

Compared to conventional bilingual translation systems, massively multilingual machine translation is appealing because a single model can translate into multiple languages and benefit from knowledge transfer for low resource languages. On the other hand, massively multilingual models suffer from the curse of multilinguality, unless scaling their size massively, which increases their training and inference costs. Sparse Mixture-of-Experts models are a way to drastically increase model capacity without the need for a proportional amount of computing. The recently released NLLB-200 is an example of such a model. It covers 202 languages but requires at least four 32GB GPUs just for inference. In this work, we propose a pruning method that allows the removal of up to 80\% of experts with a negligible loss in translation quality, which makes it feasible to run the model on a single 32GB GPU. Further analysis suggests that our pruning metrics allow to identify language-specific experts and prune non-relevant experts for a given language pair.