7 citations · 24 across the 16 of their papers we have counts for
18 papers
Cross-lingual Calibration of Pre-Generation Success Probes for Multilingual LLM Routing
Andrea Paganelli, Stefano Civelli, Pietro Bernardelle +1
Pre-generation success probes estimate response correctness from a language model's hidden activations before decoding, enabling cost-aware routing. While prior work has demonstrat…
Definitional Sensitivity in Media Bias Detection: A Multi-Definition Dataset and Benchmark
Martin Wessel, Timo Spinde, Jürgen Pfeffer +1
Media bias detection relies on definitions and examples that specify what counts as bias, yet these specifications often vary across datasets or remain implicit, even when given th…
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…
Political Ideology Shifts in Large Language Models
Pietro Bernardelle, Stefano Civelli, Leon Fröhling +3
Large language models (LLMs) are increasingly deployed in politically sensitive contexts, raising concerns about their susceptibility to ideological biases. In this work, we examin…
Towards Detecting Persuasion on Social Media: From Model Development to Insights on Persuasion Strategies
Elyas Meguellati, Stefano Civelli, Pietro Bernardelle +3
Political advertising plays a pivotal role in shaping public opinion and influencing electoral outcomes, often through subtle persuasive techniques embedded in broader propaganda s…
The Impact of Persona-based Political Perspectives on Hateful Content Detection
Stefano Civelli, Pietro Bernardelle, Gianluca Demartini
While pretraining language models with politically diverse content has been shown to improve downstream task fairness, such approaches require significant computational resources o…
Enhancing Media Literacy: The Effectiveness of (Human) Annotations and Bias Visualizations on Bias Detection
Timo Spinde, Fei Wu, Wolfgang Gaissmaier +2
Marking biased texts is a practical approach to increase media bias awareness among news consumers. However, little is known about the generalizability of such awareness to new top…
MiningGPT -- A Domain-Specific Large Language Model for the Mining Industry
Kurukulasooriya Fernando ana Gianluca Demartini
Recent advancements of generative LLMs (Large Language Models) have exhibited human-like language capabilities but have shown a lack of domain-specific understanding. Therefore, th…
SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs
Pietro Bernardelle, Leon Fröhling, Stefano Civelli +1
As increasingly capable large language models (LLMs) emerge, researchers have begun exploring their potential for subjective tasks. While recent work demonstrates that LLMs can be…
Mapping and Influencing the Political Ideology of Large Language Models using Synthetic Personas
Pietro Bernardelle, Leon Fröhling, Stefano Civelli +3
The analysis of political biases in large language models (LLMs) has primarily examined these systems as single entities with fixed viewpoints. While various methods exist for meas…
Optimizing LLMs with Direct Preferences: A Data Efficiency Perspective
Pietro Bernardelle, Gianluca Demartini
Aligning the output of Large Language Models (LLMs) with human preferences (e.g., by means of reinforcement learning with human feedback, or RLHF) is essential for ensuring their e…
Personas with Attitudes: Controlling LLMs for Diverse Data Annotation
Leon Fröhling, Gianluca Demartini, Dennis Assenmacher
We present a novel approach for enhancing diversity and control in data annotation tasks by personalizing large language models (LLMs). We investigate the impact of injecting diver…
Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges
Farid Ariai, Joel Mackenzie, Gianluca Demartini
Natural Language Processing (NLP) is revolutionising the way both professionals and laypersons operate in the legal field. The considerable potential for NLP in the legal sector, e…