73 citations · 129 across the 15 of their papers we have counts for
5 papers · 1 filter
Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
Clément Dumas, Chris Wendler, Veniamin Veselovsky +2
A central question in multilingual language modeling is whether large language models (LLMs) develop a universal concept representation, disentangled from specific languages. In th…
Self-Recognition in Language Models
Tim R. Davidson, Viacheslav Surkov, Veniamin Veselovsky +3
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-recogn…
The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates
Giuseppe Russo Latona, Manoel Horta Ribeiro, Tim R. Davidson +2
Journals and conferences worry that peer reviews assisted by artificial intelligence (AI), in particular, large language models (LLMs), may negatively influence the validity and fa…
Do Llamas Work in English? On the Latent Language of Multilingual Transformers
Chris Wendler, Veniamin Veselovsky, Giovanni Monea +1
We ask whether multilingual language models trained on unbalanced, English-dominated corpora use English as an internal pivot language -- a question of key importance for understan…
Evaluating Language Model Agency through Negotiations
Tim R. Davidson, Veniamin Veselovsky, Martin Josifoski +4
We introduce an approach to evaluate language model (LM) agency using negotiation games. This approach better reflects real-world use cases and addresses some of the shortcomings o…