2 citations · 3 across the 12 of their papers we have counts for
14 papers
ARGUS: Role-Aware Event Knowledge Graphs for U.S. Employment-Discrimination Complaints
Sriram Kannan, Swetha Saseendran, Vishnu Vardhan Reddy Kandi +3
U.S. employment-discrimination complaints describe complex event sequences that are not explicitly captured by lexical or embedding-based representations alone. We present ARGUS, a…
When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public Companies
Abhinav Havaldar, Enrico Santus
Retrieval-augmented generation (RAG) is widely assumed to mitigate factual errors in large language models (LLMs), but it remains unclear whether retrieval uniformly compensates fo…
GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
Paolo Pedinotti, Enrico Santus
Retrieval-Augmented Generation (RAG) systems increasingly employ multiple LLM agents. Yet, most prior work optimizes components in isolation rather than coordinating improvements a…
Agents in the Wild: Where Research Meets Deployment
Grace Hui Yang, Pranav N. Venkit, Hooman Sedghamiz +3
Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinating with tools and other agents are rapidly transitioning from r…
STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation
Paolo Pedinotti, Enrico Santus
The rapid growth of scientific publications makes it increasingly difficult to track and synthesize research progress. While Large Language Models (LLMs) can support automated surv…
Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law
Parisa Kordjamshidi, Samer Aslan, Madhavan Seshadri +2
Recent advances in large language models (LLMs) have significantly enhanced automated legal reasoning. Yet, it remains unclear whether their performance reflects genuine legal reas…
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan +48
Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate th…
Extensive Evaluation of Transformer-based Architectures for Adverse Drug Events Extraction
Simone Scaboro, Beatrice Portellia, Emmanuele Chersoni +2
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 Languag…
NADE: A Benchmark for Robust Adverse Drug Events Extraction in Face of Negations
Simone Scaboro, Beatrice Portelli, Emmanuele Chersoni +2
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 inv…
SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations
Hooman Sedghamiz, Shivam Raval, Enrico Santus +2
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 al…
Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media
Shivam Raval, Hooman Sedghamiz, Enrico Santus +3
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 i…
Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge
Paolo Pedinotti, Giulia Rambelli, Emmanuele Chersoni +3
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 r…
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior
Jiaming Luo, Frederik Hartmann, Enrico Santus +2
Most undeciphered lost languages exhibit two characteristics that pose significant decipherment challenges: (1) the scripts are not fully segmented into words; (2) the closest know…
Towards Debiasing Fact Verification Models
Tal Schuster, Darsh J Shah, Yun Jie Serene Yeo +3
Fact verification requires validating a claim in the context of evidence. We show, however, that in the popular FEVER dataset this might not necessarily be the case. Claim-only cla…