18 citations · 74 across the 22 of their papers we have counts for
23 papers
WorldBench: Culturally Grounded Benchmark for Multilingual Agents
Leonardo Ranaldi, Sherrie Shen, Jushi Kai +1
Despite the growing use of LLM-powered agents to solve multi-step tasks in complex environments, existing benchmarks rarely test state preservation, performance across languages, a…
Neurosymbolic Clinical Trial Matching via LLM-Driven Abduction and Logical Verification
Baiyang Qu, Leonardo Ranaldi, Xi Wang +1
Large Language Models (LLMs) offer a promising path to automate Clinical Trial Matching (CTM), but still struggle with the deterministic verification required for complex eligibili…
Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models
Gabriele Maraia, Marco Valentino, Fabio Massimo Zanzotto +1
Large Language Models (LLMs) often struggle with deductive judgment in syllogistic reasoning, systematically conflating semantic plausibility with formal validity a phenomenon know…
Challenging the Abilities of Large Language Models in Italian: a Community Initiative
Malvina Nissim, Danilo Croce, Viviana Patti +78
The rapid progress of Large Language Models (LLMs) has transformed natural language processing and broadened its impact across research and society. Yet, systematic evaluation of t…
Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies
Mael Jullien, Marco Valentino, Leonardo Ranaldi +1
Recent works on large language models (LLMs) have demonstrated the impact of prompting strategies and fine-tuning techniques on their reasoning capabilities. Yet, their effectivene…
Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs
Federico Ranaldi, Andrea Zugarini, Leonardo Ranaldi +1
We introduce the concept of protoknowledge to formalize and measure how sequences of tokens encoding Knowledge Graphs are internalized during pretraining and utilized at inference…
Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentations
Leonardo Ranaldi, Federico Ranaldi, Fabio Massimo Zanzotto +2
Retrieval-augmented generation (RAG) is key to enhancing large language models (LLMs) to systematically access richer factual knowledge. Yet, using RAG brings intrinsic challenges,…
Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task
Leonardo Ranaldi, Barry Haddow, Alexandra Birch
Retrieval-augmented generation (RAG) has become a cornerstone of contemporary NLP, enhancing large language models (LLMs) by allowing them to access richer factual contexts through…
MeMo: Towards Language Models with Associative Memory Mechanisms
Fabio Massimo Zanzotto, Elena Sofia Ruzzetti, Giancarlo A. Xompero +6
Memorization is a fundamental ability of Transformer-based Large Language Models, achieved through learning. In this paper, we propose a paradigm shift by designing an architecture…
Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
Leonardo Ranaldi, Marco Valentino, Andrè Freitas
Chain-of-Though (CoT) represents a common strategy for reasoning in Large Language Models (LLMs) by decomposing complex tasks into intermediate inference steps. However, explanatio…
Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations
Leonardo Ranaldi, Marco Valentino, Andrè Freitas
Retrieval-augmented generation (RAG) has emerged as a critical mechanism in contemporary NLP to support Large Language Models(LLMs) in systematically accessing richer factual conte…
Animate, or Inanimate, That is the Question for Large Language Models
Leonardo Ranaldi, Giulia Pucci, Fabio Massimo Zanzotto
The cognitive essence of humans is deeply intertwined with the concept of animacy, which plays an essential role in shaping their memory, vision, and multi-layered language underst…
Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models
Leonardo Ranaldi, Andrè Freitas
The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust L…
Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation
Federico Ranaldi, Elena Sofia Ruzzetti, Dario Onorati +5
Understanding textual description to generate code seems to be an achieved capability of instruction-following Large Language Models (LLMs) in zero-shot scenario. However, there is…
When Large Language Models contradict humans? Large Language Models' Sycophantic Behaviour
Leonardo Ranaldi, Giulia Pucci
Large Language Models have been demonstrating broadly satisfactory generative abilities for users, which seems to be due to the intensive use of human feedback that refines respons…
Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
Leonardo Ranaldi, Giulia Pucci, Federico Ranaldi +2
Reasoning methods, best exemplified by the well-known Chain-of-Thought (CoT), empower the reasoning abilities of Large Language Models (LLMs) by eliciting them to solve complex tas…
HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
Leonardo Ranaldi, Fabio Massimo Zanzotto
Instruction-tuned Large Language Models (It-LLMs) have been exhibiting outstanding abilities to reason around cognitive states, intentions, and reactions of all people involved, le…
Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrations
Leonardo Ranaldi, Giulia Pucci, Andre Freitas
The language ability of Large Language Models (LLMs) is often unbalanced towards English because of the imbalance in the distribution of the pre-training data. This disparity is de…
PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
Leonardo Ranaldi, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto
Pre-trained Language Models such as BERT are impressive machines with the ability to memorize, possibly generalized learning examples. We present here a small, focused contribution…
A Trip Towards Fairness: Bias and De-Biasing in Large Language Models
Leonardo Ranaldi, Elena Sofia Ruzzetti, Davide Venditti +2
Cheap-to-Build Very Large-Language Models (CtB-LLMs) with affordable training are emerging as the next big revolution in natural language processing and understanding. These CtB-LL…
Exploring Linguistic Properties of Monolingual BERTs with Typological Classification among Languages
Elena Sofia Ruzzetti, Federico Ranaldi, Felicia Logozzo +3
The impressive achievements of transformers force NLP researchers to delve into how these models represent the underlying structure of natural language. In this paper, we propose a…
The Dark Side of the Language: Pre-trained Transformers in the DarkNet
Leonardo Ranaldi, Aria Nourbakhsh, Arianna Patrizi +4
Pre-trained Transformers are challenging human performances in many NLP tasks. The massive datasets used for pre-training seem to be the key to their success on existing tasks. In…
Lacking the embedding of a word? Look it up into a traditional dictionary
Elena Sofia Ruzzetti, Leonardo Ranaldi, Michele Mastromattei +2
Word embeddings are powerful dictionaries, which may easily capture language variations. However, these dictionaries fail to give sense to rare words, which are surprisingly often…