arXiv subjects

Caio Corro

Publications and source records attributed to Caio Corro.

At least 19 recordsLinked to original sources

arXiv2026

REDSI: Addressing the Reproducibility and Evaluation Consistency of Differentiable Search Indexing for Document Retrieval

The differentiable search index (DSI) framework (Tay et al., 2022) has become the de facto baseline for generative retrieval. However, DSI is hard to reproduce: no public implementation covers all three original document identifier types (atomic, naive, semantic), reported results vary widely, and the ubiquitous NQ320K dataset is built from Natural Questions through diverse and underspecified preprocessing. We introduce ReDSI, the first open-source DSI implementation supporting all three identifier types, together with a parameterizable and well-documented NQ320K construction pipeline. Experimentally, we achieve results that are competitive with or stronger than previous DSI baselines. Moreover, we conduct extensive experiments under model downscaling, covering retrieval effectiveness, parameter efficiency, training methods and decoding strategies, opening novel directions for future research.

cs.IR↗

arXiv2026

On the Rejection Criterion for Proxy-based Test-time Alignment

Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned) model. The implicit reward approach skews the large model distribution, whereas the nudging approach defers the generation of the next token to the small aligned model when the large base one is unconfident about its outcome. In this work, we first show that both approaches can be reduced to sampling from similar graphical models, where they differ only in the definition of a rejection criterion (or distribution). Moreover, we argue that the confidence criterion is ill-motivated due to linguistic phenomena like ambiguous phrasing. We propose a novel rejection criterion based on a conservative confidence bet. Experimentally, our novel approach outperforms previous work on several datasets.

cs.CL↗

arXiv2026

Suffix-Constrained Greedy Search Algorithms for Causal Language Models

Large language models (LLMs) are powerful tools that have found applications beyond human-machine interfaces and chatbots. Beside free-form generation, there has been an interest in constrained generation, a setting where LLMs are constrained to generate well-formed outputs with respect to the language defined by a formal grammar. Although appealing, this setting may be over restrictive for downstream applications. For example, many LLM tasks require the model to reason freely before generating its final response in a specific format. In this work, we introduce suffix-constrained generation, a constrained generation setting in which only the end of the response is constrained by a grammar, a scenario that is not supported by existing constrained generation methods. We introduce several suffix-constrained generation algorithms that are based on greedy search. We experiment on several datasets, and show that our approach allows to guarantee suffix constraints without having a negative impact on results, and even improving them in many settings.

cs.CL↗

arXiv2026

A Study on Building Efficient Zero-Shot Relation Extraction Models

Zero-shot relation extraction aims to identify relations between entity mentions using textual descriptions of novel types (i.e., previously unseen) instead of labeled training examples. Previous works often rely on unrealistic assumptions: (1) pairs of mentions are often encoded directly in the input, which prevents offline pre-computation for large scale document database querying; (2) no rejection mechanism is introduced, biasing the evaluation when using these models in a retrieval scenario where some (and often most) inputs are irrelevant and must be ignored. In this work, we study the robustness of existing zero-shot relation extraction models when adapting them to a realistic extraction scenario. To this end, we introduce a typology of existing models, and propose several strategies to build single pass models and models with a rejection mechanism. We adapt several state-of-the-art tools, and compare them in this challenging setting, showing that no existing work is really robust to realistic assumptions, but overall AlignRE (Li et al., 2024) performs best along all criteria.

cs.CL↗

arXiv2026

Fast and General Automatic Differentiation for Finite-State Methods

We propose a new method, that we coined the ``morphism-trick'', to integrate custom implementations of vector-Jacobian products in automatic differentiation softwares, applicable to a wide range of semiring-based computations. Our approach leads to efficient and semiring-agnostic implementations of the backward pass of dynamic programming algorithms. For the particular case of finite-state methods, we introduce an algorithm that computes and differentiates the $\oplus$-sum of all paths' weight of a finite-state automaton. Results show that, with minimal effort from the user, our novel library allows computing the gradient of a function w.r.t. to the weights of a finite state automaton orders of magnitude faster than state-of-the-art automatic differentiation systems. Implementations are made available via an open-source library distributed under a permissive license.

cs.FL↗

arXiv2025

Kad: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral

Several previous works concluded that the largest part of generation capabilities of large language models (LLM) are learned (early) during pre-training. However, LLMs still require further alignment to adhere to downstream task requirements and stylistic preferences, among other desired properties. As LLMs continue to scale in terms of size, the computational cost of alignment procedures increase prohibitively. In this work, we propose a novel approach to circumvent these costs via proxy-based test-time alignment, i.e. using guidance from a small aligned model. Our approach can be described as a token-specific cascading method, where the token-specific deferral rule is reduced to 0-1 knapsack problem. In this setting, we derive primal and dual approximations of the optimal deferral decision. We experimentally show the benefits of our method both in task performance and speculative decoding speed.

cs.CL↗

arXiv2025

DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures

We introduce DocPolarBERT, a layout-aware BERT model for document understanding that eliminates the need for absolute 2D positional embeddings. We extend self-attention to take into account text block positions in relative polar coordinate system rather than the Cartesian one. Despite being pre-trained on a dataset more than six times smaller than the widely used IIT-CDIP corpus, DocPolarBERT achieves state-of-the-art results. These results demonstrate that a carefully designed attention mechanism can compensate for reduced pre-training data, offering an efficient and effective alternative for document understanding.

cs.CL↗

arXiv2025

Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms

We propose a novel discriminative model for sequence labeling called Bregman conditional random fields (BCRF). Contrary to standard linear-chain conditional random fields, BCRF allows fast parallelizable inference algorithms based on iterative Bregman projections. We show how such models can be learned using Fenchel-Young losses, including extension for learning from partial labels. Experimentally, our approach delivers comparable results to CRF while being faster, and achieves better results in highly constrained settings compared to mean field, another parallelizable alternative.

cs.LG↗

arXiv2025

Nested Named Entity Recognition as Single-Pass Sequence Labeling

We cast nested named entity recognition (NNER) as a sequence labeling task by leveraging prior work that linearizes constituency structures, effectively reducing the complexity of this structured prediction problem to straightforward token classification. By combining these constituency linearizations with pretrained encoders, our method captures nested entities while performing exactly n tagging actions. Our approach achieves competitive performance compared to less efficient systems, and it can be trained using any off-the-shelf sequence labeling library.

cs.CL↗

arXiv2025

EuroBERT: Scaling Multilingual Encoders for European Languages

General-purpose multilingual vector representations, used in retrieval, regression and classification, are traditionally obtained from bidirectional encoder models. Despite their wide applicability, encoders have been recently overshadowed by advances in generative decoder-only models. However, many innovations driving this progress are not inherently tied to decoders. In this paper, we revisit the development of multilingual encoders through the lens of these advances, and introduce EuroBERT, a family of multilingual encoders covering European and widely spoken global languages. Our models outperform existing alternatives across a diverse range of tasks, spanning multilingual capabilities, mathematics, and coding, and natively supporting sequences of up to 8,192 tokens. We also examine the design decisions behind EuroBERT, offering insights into our dataset composition and training pipeline. We publicly release the EuroBERT models, including intermediate training checkpoints, together with our training framework.

cs.CL↗

arXiv2024

Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain

Generic pre-trained neural networks may struggle to produce good results in specialized domains like finance and insurance. This is due to a domain mismatch between training data and downstream tasks, as in-domain data are often scarce due to privacy constraints. In this work, we compare different pre-training strategies for LayoutLM. We show that using domain-relevant documents improves results on a named-entity recognition (NER) problem using a novel dataset of anonymized insurance-related financial documents called Payslips. Moreover, we show that we can achieve competitive results using a smaller and faster model.

cs.CL↗

arXiv2024

Few-Shot Domain Adaptation for Named-Entity Recognition via Joint Constrained k-Means and Subspace Selection

Named-entity recognition (NER) is a task that typically requires large annotated datasets, which limits its applicability across domains with varying entity definitions. This paper addresses few-shot NER, aiming to transfer knowledge to new domains with minimal supervision. Unlike previous approaches that rely solely on limited annotated data, we propose a weakly supervised algorithm that combines small labeled datasets with large amounts of unlabeled data. Our method extends the k-means algorithm with label supervision, cluster size constraints and domain-specific discriminative subspace selection. This unified framework achieves state-of-the-art results in few-shot NER on several English datasets.

cs.CL↗

arXiv2024

A fast and sound tagging method for discontinuous named-entity recognition

We introduce a novel tagging scheme for discontinuous named entity recognition based on an explicit description of the inner structure of discontinuous mentions. We rely on a weighted finite state automaton for both marginal and maximum a posteriori inference. As such, our method is sound in the sense that (1) well-formedness of predicted tag sequences is ensured via the automaton structure and (2) there is an unambiguous mapping between well-formed sequences of tags and (discontinuous) mentions. We evaluate our approach on three English datasets in the biomedical domain, and report comparable results to state-of-the-art while having a way simpler and faster model.

cs.CL↗

arXiv2024

Sparse Logistic Regression with High-order Features for Automatic Grammar Rule Extraction from Treebanks

Descriptive grammars are highly valuable, but writing them is time-consuming and difficult. Furthermore, while linguists typically use corpora to create them, grammar descriptions often lack quantitative data. As for formal grammars, they can be challenging to interpret. In this paper, we propose a new method to extract and explore significant fine-grained grammar patterns and potential syntactic grammar rules from treebanks, in order to create an easy-to-understand corpus-based grammar. More specifically, we extract descriptions and rules across different languages for two linguistic phenomena, agreement and word order, using a large search space and paying special attention to the ranking order of the extracted rules. For that, we use a linear classifier to extract the most salient features that predict the linguistic phenomena under study. We associate statistical information to each rule, and we compare the ranking of the model's results to those of other quantitative and statistical measures. Our method captures both well-known and less well-known significant grammar rules in Spanish, French, and Wolof.

cs.CL↗

arXiv2024

SaulLM-7B: A pioneering Large Language Model for Law

In this paper, we introduce SaulLM-7B, a large language model (LLM) tailored for the legal domain. With 7 billion parameters, SaulLM-7B is the first LLM designed explicitly for legal text comprehension and generation. Leveraging the Mistral 7B architecture as its foundation, SaulLM-7B is trained on an English legal corpus of over 30 billion tokens. SaulLM-7B exhibits state-of-the-art proficiency in understanding and processing legal documents. Additionally, we present a novel instructional fine-tuning method that leverages legal datasets to further enhance SaulLM-7B's performance in legal tasks. SaulLM-7B is released under the MIT License.

cs.CL↗

arXiv2024

CroissantLLM: A Truly Bilingual French-English Language Model

We introduce CroissantLLM, a 1.3B language model pretrained on a set of 3T English and French tokens, to bring to the research and industrial community a high-performance, fully open-sourced bilingual model that runs swiftly on consumer-grade local hardware. To that end, we pioneer the approach of training an intrinsically bilingual model with a 1:1 English-to-French pretraining data ratio, a custom tokenizer, and bilingual finetuning datasets. We release the training dataset, notably containing a French split with manually curated, high-quality, and varied data sources. To assess performance outside of English, we craft a novel benchmark, FrenchBench, consisting of an array of classification and generation tasks, covering various orthogonal aspects of model performance in the French Language. Additionally, rooted in transparency and to foster further Large Language Model research, we release codebases, and dozens of checkpoints across various model sizes, training data distributions, and training steps, as well as fine-tuned Chat models, and strong translation models. We evaluate our model through the FMTI framework, and validate 81 % of the transparency criteria, far beyond the scores of even most open initiatives. This work enriches the NLP landscape, breaking away from previous English-centric work in order to strengthen our understanding of multilinguality in language models.

cs.CL↗

arXiv2023

Structural generalization in COGS: Supertagging is (almost) all you need

In many Natural Language Processing applications, neural networks have been found to fail to generalize on out-of-distribution examples. In particular, several recent semantic parsing datasets have put forward important limitations of neural networks in cases where compositional generalization is required. In this work, we extend a neural graph-based semantic parsing framework in several ways to alleviate this issue. Notably, we propose: (1) the introduction of a supertagging step with valency constraints, expressed as an integer linear program; (2) a reduction of the graph prediction problem to the maximum matching problem; (3) the design of an incremental early-stopping training strategy to prevent overfitting. Experimentally, our approach significantly improves results on examples that require structural generalization in the COGS dataset, a known challenging benchmark for compositional generalization. Overall, our results confirm that structural constraints are important for generalization in semantic parsing.

cs.CL↗

arXiv2023

On graph-based reentrancy-free semantic parsing

We propose a novel graph-based approach for semantic parsing that resolves two problems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both MAP inference and latent tag anchoring (required for weakly-supervised learning) are NP-hard problems. We propose two optimization algorithms based on constraint smoothing and conditional gradient to approximately solve these inference problems. Experimentally, our approach delivers state-of-the-art results on Geoquery, Scan and Clevr, both for i.i.d. splits and for splits that test for compositional generalization.

cs.CL↗