arXiv subjects

Enrico Santus

Publications and source records attributed to Enrico Santus.

At least 19 recordsLinked to original sources

arXiv2026

When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companies

Retrieval-augmented generation (RAG) is widely assumed to mitigate factual errors in large language models (LLMs), but it remains unclear whether retrieval uniformly compensates for missing knowledge. We study this question in a controlled factual QA setting over public companies, constructing a benchmark of approximately 2,000 firms across global equity indices. We evaluate six LLMs on four atomic attributes under four conditions: no-context, perfect context, misleading context, and distraction context. We find strong geographic disparities in no-context accuracy, indicating uneven parametric knowledge. While perfect context improves performance, it does not eliminate these gaps: gains are correlated with baseline accuracy, suggesting retrieval effectiveness is coupled to internal representations. Under misleading context, models frequently copy incorrect information. Larger models improve overall performance but do not remove these structural effects. These results challenge the view of RAG as a universal corrective and highlight the interaction between model knowledge, context quality, and entity representation.

cs.CL↗

arXiv2026

GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG

Retrieval-Augmented Generation (RAG) systems increasingly employ multiple LLM agents. Yet, most prior work optimizes components in isolation rather than coordinating improvements across the pipeline. We introduce GRADRAG, a framework for cross-component prompt adaptation that models the RAG pipeline as a computational graph and propagates structured evaluation feedback to update upstream agents. An Evaluator critiques downstream answers and supporting evidence, producing actionable feedback that a Prompt Optimizer uses to iteratively update adaptive agents, such as retrievers, graph constructors, and answerers. The Evaluator also triggers early stopping when the output is deemed satisfactory. We evaluate GRADRAG on the SQUALITY and QMSUM benchmarks under two retrieval paradigms: flat chunk-based retrieval using IRCoT-style query refinement (Trivedi et al., 2023), and graph-based retrieval that constructs and iteratively enriches an entity-relation graph from the document. Across both settings, GRADRAG consistently outperforms one-step refinement baselines that update only the final generator, achieving a 12-15 percentage point net preference margin in LLM-judged pairwise comparisons, with most gains realized within two refinement iterations.

cs.CL↗

arXiv2026

Agents in the Wild: Where Research Meets Deployment

Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinating with tools and other agents are rapidly transitioning from research prototypes to production scale deployments across domains such as software engineering, scientific discovery, and finance. While academic work has emphasized benchmarks and algorithmic innovation, deployment raises new challenges around robustness, safety, and reliability. This tutorial brings together researchers and practitioners to explore advances in reasoning and planning, multi agent coordination, and evaluation, highlighting open challenges arising from deployment experience. Through applied case studies in pharmaceutical discovery and financial systems, we analyze common design patterns that make agentic systems successful, and discuss practical mitigation strategies for failure modes, such as verification pipelines, fallback mechanisms, and human in the loop supervision. Attendees will gain a comprehensive view of the field along with concrete design patterns, evaluation checklists, and templates for safe and reliable deployment across industries.

cs.AI↗

arXiv2026

Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law

Recent advances in large language models (LLMs) have significantly enhanced automated legal reasoning. Yet, it remains unclear whether their performance reflects genuine legal reasoning ability or artifacts of data contamination. We present a comprehensive empirical study of tax law reasoning approaches and implement a contamination detection protocol to rigorously assess LLM reliability. We show that performance can be inflated by contamination. Building on this analysis, we conduct a systematic evaluation, comparing monolithic LLMs with hybrid systems that translate statutory text into formal representations and delegate inference to symbolic solvers. We build a novel test suite designed to probe generalization to unseen documents via case and rule variations. Our findings indicate that legal reasoning is inherently compositional and that neuro-symbolic frameworks offer a more reliable and robust foundation for legal AI, as well as improved generalization to unobserved situations.

cs.AI↗

arXiv2026

STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation

The rapid growth of scientific publications makes it increasingly difficult to track and synthesize research progress. While Large Language Models (LLMs) can support automated survey generation, existing methods retrieve unstructured data and require models to infer conceptual, methodological, and taxonomic relations from raw text at generation time. We introduce STRUCTSURVEY, a hierarchical multi-agent framework that shifts structural reasoning from generation to retrieval by dynamically constructing graph-based representations of entities, relations, and topical taxonomies. We evaluate STRUCTSURVEY on a new reference-grounded benchmark of ACL survey papers for reproducible long-form scientific summarization. Compared with embedding-only retrieval baselines, STRUCTSURVEY improves ROUGE-1 recall by +2.9 and ROUGE-2 recall by +1.0 on average, without reducing precision. It also improves LLM-as-a-Judge ratings for logical structure, depth, and synthesis, showing that explicit structural retrieval yields surveys closer to human-written organization and reasoning.

cs.IR↗

arXiv2025

MetaGraph: A Large-Scale Meta-Analysis of GenAI in Financial NLP (2022-2025)

Financial NLP has evolved rapidly since late 2022, outpacing narrative surveys. We introduce MetaGraph, a methodology for extracting typed knowledge graphs from scientific corpora using ontology-guided LLM extraction to enable structured, large-scale trend analysis. Applied to 681 papers on GenAI in Finance (2022-2025), MetaGraph reveals three phases: early LLM-driven expansion of tasks and datasets, growing emphasis on limitations and risk, and a shift toward modular, system-oriented methods (e.g., retrieval-augmented designs). We release the resulting resource and artifacts to support reproducible meta-analysis and future monitoring of the field.

cs.CL↗

arXiv2025

WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside a training dataset (1 million instances). Our findings show that while VLMs perform better with correct location context, they struggle with adversarial contexts and predicting specific regional cuisines and languages. To support future research, we release a knowledge base with annotated food entries and images along with the VQA data.

cs.CL↗

arXiv2023

Extensive Evaluation of Transformer-based Architectures for Adverse Drug Events Extraction

Adverse Event (ADE) extraction is one of the core tasks in digital pharmacovigilance, especially when applied to informal texts. This task has been addressed by the Natural Language Processing community using large pre-trained language models, such as BERT. Despite the great number of Transformer-based architectures used in the literature, it is unclear which of them has better performances and why. Therefore, in this paper we perform an extensive evaluation and analysis of 19 Transformer-based models for ADE extraction on informal texts. We compare the performance of all the considered models on two datasets with increasing levels of informality (forums posts and tweets). We also combine the purely Transformer-based models with two commonly-used additional processing layers (CRF and LSTM), and analyze their effect on the models performance. Furthermore, we use a well-established feature importance technique (SHAP) to correlate the performance of the models with a set of features that describe them: model category (AutoEncoding, AutoRegressive, Text-to-Text), pretraining domain, training from scratch, and model size in number of parameters. At the end of our analyses, we identify a list of take-home messages that can be derived from the experimental data.

cs.CL↗

arXiv2022

Generalizing over Long Tail Concepts for Medical Term Normalization

Medical term normalization consists in mapping a piece of text to a large number of output classes. Given the small size of the annotated datasets and the extremely long tail distribution of the concepts, it is of utmost importance to develop models that are capable to generalize to scarce or unseen concepts. An important attribute of most target ontologies is their hierarchical structure. In this paper we introduce a simple and effective learning strategy that leverages such information to enhance the generalizability of both discriminative and generative models. The evaluation shows that the proposed strategy produces state-of-the-art performance on seen concepts and consistent improvements on unseen ones, allowing also for efficient zero-shot knowledge transfer across text typologies and datasets.

cs.CL↗

arXiv2022

AILAB-Udine@SMM4H 22: Limits of Transformers and BERT Ensembles

This paper describes the models developed by the AILAB-Udine team for the SMM4H 22 Shared Task. We explored the limits of Transformer based models on text classification, entity extraction and entity normalization, tackling Tasks 1, 2, 5, 6 and 10. The main take-aways we got from participating in different tasks are: the overwhelming positive effects of combining different architectures when using ensemble learning, and the great potential of generative models for term normalization.

cs.CL↗

arXiv2022

Increasing Adverse Drug Events extraction robustness on social media: case study on negation and speculation

In the last decade, an increasing number of users have started reporting Adverse Drug Events (ADE) on social media platforms, blogs, and health forums. Given the large volume of reports, pharmacovigilance has focused on ways to use Natural Language Processing (NLP) techniques to rapidly examine these large collections of text, detecting mentions of drug-related adverse reactions to trigger medical investigations. However, despite the growing interest in the task and the advances in NLP, the robustness of these models in face of linguistic phenomena such as negations and speculations is an open research question. Negations and speculations are pervasive phenomena in natural language, and can severely hamper the ability of an automated system to discriminate between factual and nonfactual statements in text. In this paper we take into consideration four state-of-the-art systems for ADE detection on social media texts. We introduce SNAX, a benchmark to test their performance against samples containing negated and speculated ADEs, showing their fragility against these phenomena. We then introduce two possible strategies to increase the robustness of these models, showing that both of them bring significant increases in performance, lowering the number of spurious entities predicted by the models by 60% for negation and 80% for speculations.

cs.CL↗

arXiv2021

NADE: A Benchmark for Robust Adverse Drug Events Extraction in Face of Negations

Adverse Drug Event (ADE) extraction models can rapidly examine large collections of social media texts, detecting mentions of drug-related adverse reactions and trigger medical investigations. However, despite the recent advances in NLP, it is currently unknown if such models are robust in face of negation, which is pervasive across language varieties. In this paper we evaluate three state-of-the-art systems, showing their fragility against negation, and then we introduce two possible strategies to increase the robustness of these models: a pipeline approach, relying on a specific component for negation detection; an augmentation of an ADE extraction dataset to artificially create negated samples and further train the models. We show that both strategies bring significant increases in performance, lowering the number of spurious entities predicted by the models. Our dataset and code will be publicly released to encourage research on the topic.

cs.CL↗

arXiv2021

SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations

While contrastive learning is proven to be an effective training strategy in computer vision, Natural Language Processing (NLP) is only recently adopting it as a self-supervised alternative to Masked Language Modeling (MLM) for improving sequence representations. This paper introduces SupCL-Seq, which extends the supervised contrastive learning from computer vision to the optimization of sequence representations in NLP. By altering the dropout mask probability in standard Transformer architectures, for every representation (anchor), we generate augmented altered views. A supervised contrastive loss is then utilized to maximize the system's capability of pulling together similar samples (e.g., anchors and their altered views) and pushing apart the samples belonging to the other classes. Despite its simplicity, SupCLSeq leads to large gains in many sequence classification tasks on the GLUE benchmark compared to a standard BERTbase, including 6% absolute improvement on CoLA, 5.4% on MRPC, 4.7% on RTE and 2.6% on STSB. We also show consistent gains over self supervised contrastively learned representations, especially in non-semantic tasks. Finally we show that these gains are not solely due to augmentation, but rather to a downstream optimized sequence representation. Code: https://github.com/hooman650/SupCL-Seq

cs.CL↗

arXiv2021

Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media

Adverse Events (AE) are harmful events resulting from the use of medical products. Although social media may be crucial for early AE detection, the sheer scale of this data makes it logistically intractable to analyze using human agents, with NLP representing the only low-cost and scalable alternative. In this paper, we frame AE Detection and Extraction as a sequence-to-sequence problem using the T5 model architecture and achieve strong performance improvements over competitive baselines on several English benchmarks (F1 = 0.71, 12.7% relative improvement for AE Detection; Strict F1 = 0.713, 12.4% relative improvement for AE Extraction). Motivated by the strong commonalities between AE-related tasks, the class imbalance in AE benchmarks and the linguistic and structural variety typical of social media posts, we propose a new strategy for multi-task training that accounts, at the same time, for task and dataset characteristics. Our multi-task approach increases model robustness, leading to further performance gains. Finally, our framework shows some language transfer capabilities, obtaining higher performance than Multilingual BERT in zero-shot learning on French data.

cs.CL↗

arXiv2021

Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge

Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate. While much work has been devoted to modeling the typicality relation between verbs and arguments in isolation, in this paper we take a broader perspective by assessing whether and to what extent computational approaches have access to the information about the typicality of entire events and situations described in language (Generalized Event Knowledge). Given the recent success of Transformers Language Models (TLMs), we decided to test them on a benchmark for the \textit{dynamic estimation of thematic fit}. The evaluation of these models was performed in comparison with SDM, a framework specifically designed to integrate events in sentence meaning representations, and we conducted a detailed error analysis to investigate which factors affect their behavior. Our results show that TLMs can reach performances that are comparable to those achieved by SDM. However, additional analysis consistently suggests that TLMs do not capture important aspects of event knowledge, and their predictions often depend on surface linguistic features, such as frequent words, collocations and syntactic patterns, thereby showing sub-optimal generalization abilities.

cs.CL↗

arXiv2021

Improving Adverse Drug Event Extraction with SpanBERT on Different Text Typologies

In recent years, Internet users are reporting Adverse Drug Events (ADE) on social media, blogs and health forums. Because of the large volume of reports, pharmacovigilance is seeking to resort to NLP to monitor these outlets. We propose for the first time the use of the SpanBERT architecture for the task of ADE extraction: this new version of the popular BERT transformer showed improved capabilities with multi-token text spans. We validate our hypothesis with experiments on two datasets (SMM4H and CADEC) with different text typologies (tweets and blog posts), finding that SpanBERT combined with a CRF outperforms all the competitors on both of them.

cs.CL↗

arXiv2020

Deciphering Undersegmented Ancient Scripts Using Phonetic Prior

Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest known language is not determined. We propose a decipherment model that handles both of these challenges by building on rich linguistic constraints reflecting consistent patterns in historical sound change. We capture the natural phonological geometry by learning character embeddings based on the International Phonetic Alphabet (IPA). The resulting generative framework jointly models word segmentation and cognate alignment, informed by phonological constraints. We evaluate the model on both deciphered languages (Gothic, Ugaritic) and an undeciphered one (Iberian). The experiments show that incorporating phonetic geometry leads to clear and consistent gains. Additionally, we propose a measure for language closeness which correctly identifies related languages for Gothic and Ugaritic. For Iberian, the method does not show strong evidence supporting Basque as a related language, concurring with the favored position by the current scholarship.

cs.CL↗

arXiv2020

IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation

Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This task remains challenging due to a lack of supervised parallel data. Existing approaches try to explicitly disentangle content and attribute information, but this is difficult and often results in poor content-preservation and ungrammaticality. In contrast, we propose a simpler approach, Iterative Matching and Translation (IMaT), which: (1) constructs a pseudo-parallel corpus by aligning a subset of semantically similar sentences from the source and the target corpora; (2) applies a standard sequence-to-sequence model to learn the attribute transfer; (3) iteratively improves the learned transfer function by refining imperfections in the alignment. In sentiment modification and formality transfer tasks, our method outperforms complex state-of-the-art systems by a large margin. As an auxiliary contribution, we produce a publicly-available test set with human-generated transfer references.

cs.CL↗