arXiv subjects

Roberto Lotufo

Publications and source records attributed to Roberto Lotufo.

At least 19 recordsLinked to original sources

arXiv2026

Legal Nugget Extraction for Granular Retrieval over Long Jurisprudential Texts

Legal retrieval over jurisprudential collections is challenging because court decisions are long, heterogeneous documents whose relevant legal thesis may occupy only a small portion of the text. This paper asks whether legal nuggets, defined as short and self-contained legal theses extracted from source documents, can improve dense retrieval over Brazilian legal collections. We propose a pipeline that extracts nuggets from each document, indexes them with embeddings, retrieves nugget-level evidence, and aggregates the retrieved nuggets back to document-level rankings. We evaluate this approach on four Portuguese legal retrieval benchmarks from the JUA ecosystem, reporting NDCG@10, MAP@10, and MRR@10. Nugget retrieval substantially improves the two jurisprudential datasets: on JUA-Juris, NDCG@10 increases from 0.10265 to 0.20461, and on JurisTCU from 0.20898 to 0.32696. However, it underperforms full-document retrieval on NormasTCU and BR-TaxQA, and an embedding-model ablation shows that strong domain-adapted retrievers can remain better in the full-document setting. The results demonstrate that legal nuggets can be useful for jurisprudence search, especially when queries are formulated as legal theses, but they may not transfer equally well to other legal retrieval scenarios.

cs.IR↗

arXiv2026

Domain-Adaptive Dense Retrieval for Brazilian Legal Search

Brazilian legal retrieval is heterogeneous, covering case law, legislation, and question-based search. This makes training dense retrievers a trade-off between stronger domain specialization and broader robustness across retrieval types of search. In this paper, we explore this trade-off using three training setups based on Qwen3-Embedding-4B: a base model with no fine-tuning, a version trained only on legal data, and a mixed setup that combines legal data with SQuAD-pt supervised dataset. We evaluate these models on five legal datasets from the JU\'A leaderboard, along with Quati dataset as an extra Portuguese retrieval benchmark to test out-of-domain generalization. The legal-only model performs best on the most specialized legal tasks. The mixed setup keeps strong performance on legal data while offering a better overall balance, improving average NDCG@10 from 0.414 to 0.447, MRR@10 from 0.586 to 0.595, and MAP@10 from 0.270 to 0.308 across all six datasets. The biggest improvement appears on Quati, where the mixed model clearly outperforms the legal-only one. Overall, the results show that legal-only and mixed training lead to different strengths: the first is better for specialization, while the second is more robust across different types of search, especially question-based ones. Both adapted models are available on Hugging Face

cs.IR↗

arXiv2026

Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical Guidelines

Brazil's Unified Health System (SUS) relies on official clinical guidelines that define diagnostic criteria, treatments, dosages, and monitoring procedures for over 200 million citizens. Yet current LLMs perform poorly on this guideline-specific knowledge, and no benchmark evaluates clinical recall grounded in Brazilian Portuguese protocols. We address this gap by adapting Qwen2.5-14B-Instruct to the Brazilian clinical domain. From 178 official guidelines (~5.4M tokens), we generate ~70M tokens of synthetic data in three formats -- rephrases, wiki-style articles, and question-answer pairs -- using four generator LLMs. We then apply continual pre-training followed by Group Relative Policy Optimization (GRPO). We introduce HealthBench-BR, with 1,780 balanced true/false clinical assertions, and PCDT-QA, with 890 open-ended clinical questions scored by an LLM judge. Our best model achieves 83.9% on HealthBench-BR and 85.4% on PCDT-QA, outperforming GPT-5.2, Claude Sonnet 4.6, Gemini 3.1 Pro, and Google AI Overview's web-grounded RAG despite having only 14B parameters. Ablations show that generator diversity and reinforcement learning are critical to these gains. We release all datasets, benchmarks, and model weights to support reproducible clinical NLP research for Brazilian Portuguese. Code, data, and model weights are available at https://github.com/hugoabonizio/clinical-protocols-br

cs.CL↗

arXiv2026

JU\'A -- A Benchmark for Information Retrieval in Brazilian Legal Text Collections

Legal information retrieval in Portuguese remains difficult to evaluate systematically because available datasets differ widely in document type, query style, and relevance definition. We present JU\'A, a public benchmark for Brazilian legal retrieval designed to support more reproducible and comparable evaluation across heterogeneous legal collections. More broadly, JU\'A is intended not only as a benchmark, but as a continuous evaluation infrastructure for Brazilian legal IR, combining shared protocols, common ranking metrics, fixed splits when applicable, and a public leaderboard. The benchmark covers jurisprudence retrieval as well as broader legislative, regulatory, and question-driven legal search. We evaluate lexical, dense, and BM25-based reranking pipelines, including a domain-adapted Qwen embedding model fine-tuned on JU\'A-aligned supervision. Results show that the benchmark is sufficiently heterogeneous to distinguish retrieval paradigms and reveal substantial cross-dataset trade-offs. Domain adaptation yields its clearest gains on the supervision-aligned JU\'A-Juris subset, while BM25 remains highly competitive on other collections, especially in settings with strong lexical and institutional phrasing cues. Overall, JU\'A provides a practical evaluation framework for studying legal retrieval across multiple Brazilian legal domains under a common benchmark design.

cs.IR↗

arXiv2025

Comparing Knowledge Injection Methods for LLMs in a Low-Resource Regime

Large language models (LLMs) often require vast amounts of text to effectively acquire new knowledge. While continuing pre-training on large corpora or employing retrieval-augmented generation (RAG) has proven successful, updating an LLM with only a few thousand or million tokens remains challenging. In this work, we investigate the task of injecting small, unstructured information into LLMs and its relation to the catastrophic forgetting phenomenon. We use a dataset of recent news -- ensuring no overlap with the model's pre-training data -- to evaluate the knowledge acquisition by probing the model with question-answer pairs related the learned information. Starting from a continued pre-training baseline, we explored different augmentation algorithms to generate synthetic data to improve the knowledge acquisition capabilities. Our experiments show that simply continuing pre-training on limited data yields modest improvements, whereas exposing the model to diverse textual variations significantly improves the learning of new facts -- particularly with methods that induce greater variability through diverse prompting. Furthermore, we shed light on the forgetting phenomenon in small-data regimes, illustrating the delicate balance between learning new content and retaining existing capabilities. We also confirm the sensitivity of RAG-based approaches for knowledge injection, which often lead to greater degradation on control datasets compared to parametric methods. Finally, we demonstrate that models can generate effective synthetic training data themselves, suggesting a pathway toward self-improving model updates. All code and generated data used in our experiments are publicly available, providing a resource for studying efficient knowledge injection in LLMs with limited data at https://github.com/hugoabonizio/knowledge-injection-methods.

cs.CL↗

arXiv2025

RAISE: Reasoning Agent for Interactive SQL Exploration

Recent advances in large language models (LLMs) have propelled research in natural language interfaces to databases. However, most state-of-the-art text-to-SQL systems still depend on complex, multi-stage pipelines. This work proposes a novel agentic framework that unifies schema linking, query generation, and iterative refinement within a single, end-to-end component. By leveraging the intrinsic reasoning abilities of LLMs, our method emulates how humans answer questions when working with unfamiliar databases: understanding the data by formulating hypotheses, running dynamic queries to validate them, reasoning over the results, and revising outputs based on observed results. Crucially, our approach introduces a new strategy for scaling test-time computation in text-to-SQL: we scale the depth of interactive database exploration and reflection. This shift enables the model to allocate computation dynamically to better understand the data, especially useful in ambiguous and underspecified scenarios. Our experiments show that it improved the Execution Accuracy (EX) from 44.8% to 56.5% on the challenging BIRD dataset using DeepSeek-R1-Distill-Llama-70B. Furthermore, when equipped with steps to add more diversity to the answers, our agent achieves a Best-of-N accuracy of 81.8% with 8 rounds of candidate generation, rivaling the 82.79% achieved by the top-ranked published solution, while reducing engineering complexity. These findings position our unified framework as a promising alternative for building natural language interfaces to databases.

cs.AI↗

arXiv2025

BR-TaxQA-R: A Dataset for Question Answering with References for Brazilian Personal Income Tax Law, including case law

This paper presents BR-TaxQA-R, a novel dataset designed to support question answering with references in the context of Brazilian personal income tax law. The dataset contains 715 questions from the 2024 official Q\&A document published by Brazil's Internal Revenue Service, enriched with statutory norms and administrative rulings from the Conselho Administrativo de Recursos Fiscais (CARF). We implement a Retrieval-Augmented Generation (RAG) pipeline using OpenAI embeddings for searching and GPT-4o-mini for answer generation. We compare different text segmentation strategies and benchmark our system against commercial tools such as ChatGPT and Perplexity.ai using RAGAS-based metrics. Results show that our custom RAG pipeline outperforms commercial systems in Response Relevancy, indicating stronger alignment with user queries, while commercial models achieve higher scores in Factual Correctness and fluency. These findings highlight a trade-off between legally grounded generation and linguistic fluency. Crucially, we argue that human expert evaluation remains essential to ensure the legal validity of AI-generated answers in high-stakes domains such as taxation. BR-TaxQA-R is publicly available at https://huggingface.co/datasets/unicamp-dl/BR-TaxQA-R.

cs.CL↗

arXiv2024

PublicHearingBR: A Brazilian Portuguese Dataset of Public Hearing Transcripts for Summarization of Long Documents

This paper introduces PublicHearingBR, a Brazilian Portuguese dataset designed for summarizing long documents. The dataset consists of transcripts of public hearings held by the Brazilian Chamber of Deputies, paired with news articles and structured summaries containing the individuals participating in the hearing and their statements or opinions. The dataset supports the development and evaluation of long document summarization systems in Portuguese. Our contributions include the dataset, a hybrid summarization system to establish a baseline for future studies, and a discussion of evaluation metrics for summarization involving large language models, addressing the challenge of hallucination in the generated summaries. As a result of this discussion, the dataset also includes annotated data to evaluate natural language inference tasks in Portuguese.

cs.CL↗

arXiv2024

MLissard: Multilingual Long and Simple Sequential Reasoning Benchmarks

Language models are now capable of solving tasks that require dealing with long sequences consisting of hundreds of thousands of tokens. However, they often fail on tasks that require repetitive use of simple rules, even on sequences that are much shorter than those seen during training. For example, state-of-the-art LLMs can find common items in two lists with up to 20 items but fail when lists have 80 items. In this paper, we introduce MLissard, a multilingual benchmark designed to evaluate models' abilities to process and generate texts of varied lengths and offers a mechanism for controlling sequence complexity. Our evaluation of open-source and proprietary models show a consistent decline in performance across all models and languages as the complexity of the sequence increases. Surprisingly, the use of in-context examples in languages other than English helps increase extrapolation performance significantly. The datasets and code are available at https://github.com/unicamp-dl/Lissard

cs.CL↗

arXiv2024

SurveySum: A Dataset for Summarizing Multiple Scientific Articles into a Survey Section

Document summarization is a task to shorten texts into concise and informative summaries. This paper introduces a novel dataset designed for summarizing multiple scientific articles into a section of a survey. Our contributions are: (1) SurveySum, a new dataset addressing the gap in domain-specific summarization tools; (2) two specific pipelines to summarize scientific articles into a section of a survey; and (3) the evaluation of these pipelines using multiple metrics to compare their performance. Our results highlight the importance of high-quality retrieval stages and the impact of different configurations on the quality of generated summaries.

cs.CL↗

arXiv2024

Check-Eval: A Checklist-based Approach for Evaluating Text Quality

Evaluating the quality of text generated by large language models (LLMs) remains a significant challenge. Traditional metrics often fail to align well with human judgments, particularly in tasks requiring creativity and nuance. In this paper, we propose \textsc{Check-Eval}, a novel evaluation framework leveraging LLMs to assess the quality of generated text through a checklist-based approach. \textsc{Check-Eval} can be employed as both a reference-free and reference-dependent evaluation method, providing a structured and interpretable assessment of text quality. The framework consists of two main stages: checklist generation and checklist evaluation. We validate \textsc{Check-Eval} on two benchmark datasets: Portuguese Legal Semantic Textual Similarity and \textsc{SummEval}. Our results demonstrate that \textsc{Check-Eval} achieves higher correlations with human judgments compared to existing metrics, such as \textsc{G-Eval} and \textsc{GPTScore}, underscoring its potential as a more reliable and effective evaluation framework for natural language generation tasks. The code for our experiments is available at \url{https://anonymous.4open.science/r/check-eval-0DB4}

cs.CL↗

arXiv2024

ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language

Despite advancements in Natural Language Processing (NLP) and the growing availability of pretrained models, the English language remains the primary focus of model development. Continued pretraining on language-specific corpora provides a practical solution for adapting models to other languages. However, the impact of different pretraining settings on downstream tasks remains underexplored. This work introduces $\texttt{ptt5-v2}$, investigating the continued pretraining of T5 models for Portuguese. We first develop a baseline set of settings and pretrain models with sizes up to 3B parameters. Finetuning on three Portuguese downstream tasks (assin2 STS, assin2 RTE, and TweetSentBR) yields SOTA results on the latter two. We then explore the effects of different pretraining configurations, including pretraining data quality, optimization strategies, and multi-epoch pretraining. Perhaps surprisingly, their impact remains subtle compared to our baseline. We release $\texttt{ptt5-v2}$ pretrained checkpoints and their MonoT5-based finetuned $\texttt{MonoPTT5}$ rerankers on HuggingFace in their respective collections at \url{https://huggingface.co/unicamp-dl}.

cs.CL↗

arXiv2024

Measuring Cross-lingual Transfer in Bytes

Multilingual pretraining has been a successful solution to the challenges posed by the lack of resources for languages. These models can transfer knowledge to target languages with minimal or no examples. Recent research suggests that monolingual models also have a similar capability, but the mechanisms behind this transfer remain unclear. Some studies have explored factors like language contamination and syntactic similarity. An emerging line of research suggests that the representations learned by language models contain two components: a language-specific and a language-agnostic component. The latter is responsible for transferring a more universal knowledge. However, there is a lack of comprehensive exploration of these properties across diverse target languages. To investigate this hypothesis, we conducted an experiment inspired by the work on the Scaling Laws for Transfer. We measured the amount of data transferred from a source language to a target language and found that models initialized from diverse languages perform similarly to a target language in a cross-lingual setting. This was surprising because the amount of data transferred to 10 diverse target languages, such as Spanish, Korean, and Finnish, was quite similar. We also found evidence that this transfer is not related to language contamination or language proximity, which strengthens the hypothesis that the model also relies on language-agnostic knowledge. Our experiments have opened up new possibilities for measuring how much data represents the language-agnostic representations learned during pretraining.

cs.CL↗

arXiv2024

INACIA: Integrating Large Language Models in Brazilian Audit Courts: Opportunities and Challenges

This paper introduces INACIA (Instrução Assistida com Inteligência Artificial), a groundbreaking system designed to integrate Large Language Models (LLMs) into the operational framework of Brazilian Federal Court of Accounts (TCU). The system automates various stages of case analysis, including basic information extraction, admissibility examination, Periculum in mora and Fumus boni iuris analyses, and recommendations generation. Through a series of experiments, we demonstrate INACIA's potential in extracting relevant information from case documents, evaluating its legal plausibility, and formulating propositions for judicial decision-making. Utilizing a validation dataset alongside LLMs, our evaluation methodology presents a novel approach to assessing system performance, correlating highly with human judgment. These results underscore INACIA's potential in complex legal task handling while also acknowledging the current limitations. This study discusses possible improvements and the broader implications of applying AI in legal contexts, suggesting that INACIA represents a significant step towards integrating AI in legal systems globally, albeit with cautious optimism grounded in the empirical findings.

cs.CL↗

arXiv2024

Lissard: Long and Simple Sequential Reasoning Datasets

Language models are now capable of solving tasks that require dealing with long sequences consisting of hundreds of thousands of tokens. However, they often fail on tasks that require repetitive use of simple rules, even on sequences that are much shorter than those seen during training. For example, state-of-the-art LLMs can find common items in two lists with up to 20 items but fail when lists have 80 items. In this paper, we introduce Lissard, a benchmark comprising seven tasks whose goal is to assess the ability of models to process and generate wide-range sequence lengths, requiring repetitive procedural execution. Our evaluation of open-source (Mistral-7B and Mixtral-8x7B) and proprietary models (GPT-3.5 and GPT-4) show a consistent decline in performance across all models as the complexity of the sequence increases. The datasets and code are available at https://github.com/unicamp-dl/Lissard

cs.CL↗

arXiv2024

ExaRanker-Open: Synthetic Explanation for IR using Open-Source LLMs

ExaRanker recently introduced an approach to training information retrieval (IR) models, incorporating natural language explanations as additional labels. The method addresses the challenge of limited labeled examples, leading to improvements in the effectiveness of IR models. However, the initial results were based on proprietary language models such as GPT-3.5, which posed constraints on dataset size due to its cost and data privacy. In this paper, we introduce ExaRanker-Open, where we adapt and explore the use of open-source language models to generate explanations. The method has been tested using different LLMs and datasets sizes to better comprehend the effective contribution of data augmentation. Our findings reveal that incorporating explanations consistently enhances neural rankers, with benefits escalating as the LLM size increases. Notably, the data augmentation method proves advantageous even with large datasets, as evidenced by ExaRanker surpassing the target baseline by 0.6 nDCG@10 points in our study. To encourage further advancements by the research community, we have open-sourced both the code and datasets at https://github.com/unicamp-dl/ExaRanker.

cs.IR↗

arXiv2024

InRanker: Distilled Rankers for Zero-shot Information Retrieval

Despite multi-billion parameter neural rankers being common components of state-of-the-art information retrieval pipelines, they are rarely used in production due to the enormous amount of compute required for inference. In this work, we propose a new method for distilling large rankers into their smaller versions focusing on out-of-domain effectiveness. We introduce InRanker, a version of monoT5 distilled from monoT5-3B with increased effectiveness on out-of-domain scenarios. Our key insight is to use language models and rerankers to generate as much as possible synthetic "in-domain" training data, i.e., data that closely resembles the data that will be seen at retrieval time. The pipeline consists of two distillation phases that do not require additional user queries or manual annotations: (1) training on existing supervised soft teacher labels, and (2) training on teacher soft labels for synthetic queries generated using a large language model. Consequently, models like monoT5-60M and monoT5-220M improved their effectiveness by using the teacher's knowledge, despite being 50x and 13x smaller, respectively. Models and code are available at https://github.com/unicamp-dl/InRanker.

cs.IR↗

arXiv2023

InPars Toolkit: A Unified and Reproducible Synthetic Data Generation Pipeline for Neural Information Retrieval

Recent work has explored Large Language Models (LLMs) to overcome the lack of training data for Information Retrieval (IR) tasks. The generalization abilities of these models have enabled the creation of synthetic in-domain data by providing instructions and a few examples on a prompt. InPars and Promptagator have pioneered this approach and both methods have demonstrated the potential of using LLMs as synthetic data generators for IR tasks. This makes them an attractive solution for IR tasks that suffer from a lack of annotated data. However, the reproducibility of these methods was limited, because InPars' training scripts are based on TPUs -- which are not widely accessible -- and because the code for Promptagator was not released and its proprietary LLM is not publicly accessible. To fully realize the potential of these methods and make their impact more widespread in the research community, the resources need to be accessible and easy to reproduce by researchers and practitioners. Our main contribution is a unified toolkit for end-to-end reproducible synthetic data generation research, which includes generation, filtering, training and evaluation. Additionally, we provide an interface to IR libraries widely used by the community and support for GPU. Our toolkit not only reproduces the InPars method and partially reproduces Promptagator, but also provides a plug-and-play functionality allowing the use of different LLMs, exploring filtering methods and finetuning various reranker models on the generated data. We also made available all the synthetic data generated in this work for the 18 different datasets in the BEIR benchmark which took more than 2,000 GPU hours to be generated as well as the reranker models finetuned on the synthetic data. Code and data are available at https://github.com/zetaalphavector/InPars

cs.IR↗