11 papers
Persona Conditioning as an Assessor-Sensitivity Probe for LLM-Based IR Evaluation
Samaneh Mohtadi, Pietro Bernardelle, Joel Mackenzie +1
Large language models (LLMs) are increasingly used as relevance assessors in information retrieval (IR) evaluation, raising questions about how assessor framing affects judgment re…
LLMs Encode Relevance as a Layer-Wise Cross-Lingual Signal
Pietro Bernardelle, Samaneh Mohtadi, Stefano Civelli +2
Large language models (LLMs) are increasingly used in information retrieval (IR) pipelines as relevance judges and re-rankers. Yet most analyses remain output-centric, evaluating g…
Context Shapes LLMs Retrieval-Augmented Fact-Checking Effectiveness
Pietro Bernardelle, Stefano Civelli, Kevin Roitero +1
Large language models (LLMs) show strong reasoning abilities across diverse tasks, yet their performance on extended contexts remains inconsistent. While prior research has emphasi…
A Shared Geometry of Difficulty in Multilingual Language Models
Stefano Civelli, Pietro Bernardelle, Nicolò Brunello +1
Predicting problem-difficulty in large language models (LLMs) refers to estimating how difficult a task is according to the model itself, typically by training linear probes on its…
Political Advertising on Facebook During the 2022 Australian Federal Election: A Social Identity Perspective
Stefano Civelli, Pietro Bernardelle, Frank Mols +1
The spread of targeted advertising on social media platforms has revolutionized political marketing strategies. Monitoring these digital campaigns is essential for maintaining tran…
Ideology-Based LLMs for Content Moderation
Stefano Civelli, Pietro Bernardelle, Nardiena A. Pratama +1
Large language models (LLMs) are increasingly used in content moderation systems, where ensuring fairness and neutrality is essential. In this study, we examine how persona adoptio…