Publications by Robert West | EPFL Graph Search

On the conversational persuasiveness of GPT-4

Early work has found that large language models (LLMs) can generate persuasive content. However, evidence on whether they can also personalize arguments to individual attributes remains limited, despite being crucial for assessing misuse. This preregistere ...

Springer Science and Business Media LLC2025

Post Guidance for Online Communities

Robert West, Manoel Horta Ribeiro

Effective content moderation in online communities is often a delicate balance between maintaining content quality and fostering user participation. In this paper, we introduce post guidance, a novel approach to community moderation that proactively guides ...

Association for Computing Machinery (ACM)2025

Prevalence and Prevention of Large Language Model Use in Crowd Work

Robert West

ASSOC COMPUTING MACHINERY2025

Deplatforming Norm-Violating Influencers on Social Media Reduces Overall Online Attention Toward Them

Robert West, Manoel Horta Ribeiro

From politicians to podcast hosts, online platforms have systematically banned (''deplatformed'') influential users for breaking platform guidelines. Previous inquiries on the effectiveness of this intervention are inconclusive because 1) they consider onl ...

Association for Computing Machinery (ACM)2025

A Logical Fallacy-Informed Framework for Argument Generation

Boi Faltings, Robert West, Antoine Bosselut, Luca Mouchel, Debjit Paul

Despite the remarkable performance of large language models (LLMs), they still struggle with generating logically sound arguments, resulting in potential risks such as spreading misinformation. An important factor contributing to LLMs' suboptimal performan ...

Association for Computational Linguistics2025

The AI Alignment Paradox The better we align AI models with our values, the easier we may make it to realign them with opposing values

Robert West

ASSOC COMPUTING MACHINERY2025

Activation Scaling for Steering and Interpreting Language Models

Robert West

Given the prompt “Rome is in”, can we steer a language model to flip its prediction of an incorrect token “France” to a correct token “Italy” by only multiplying a few relevant activation vectors with scalars? We argue that successfully intervening on a mo ...

Association for Computational Linguistics (ACL)2024

Open access improves the dissemination of science: insights from Wikipedia

Robert West

Wikipedia is a well-known platform for disseminating knowledge, and scientific sources, such as journal articles, play a critical role in supporting its mission. The open access movement aims to make scientific knowledge openly available, and we might intu ...

2024

Self-Recognition in Language Models

Robert West, Caglar Gulcehre, Giuseppe Russo

A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recognition capabilities. Inspired by human identity verification methods, we prop ...

Association for Computational Linguistics2024

Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning

Boi Faltings, Robert West, Antoine Bosselut, Debjit Paul

Large language models (LLMs) have been shown to perform better when asked to reason step-by-step before answering a question. However, it is unclear to what degree the model's final answer is faithful to the stated reasoning steps. In this paper, we perfor ...

Association for Computational Linguistics (ACL)2024