Resultados da busca - Ortu, Francesco

When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models por Ortu, Francesco, Jin, Zhijing, Doimo, Diego, Cazzaniga, Alberto

Obter o texto integral
Obter o texto integral

Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals por Ortu, Francesco, Jin, Zhijing, Doimo, Diego, Sachan, Mrinmaya, Cazzaniga, Alberto, Schölkopf, Bernhard

Obter o texto integral
Obter o texto integral

Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing por Yadav, Neemesh, Liu, Jiarui, Ortu, Francesco, Ensafi, Roya, Jin, Zhijing, Mihalcea, Rada

Obter o texto integral
Obter o texto integral

Do LLMs Rewrite History? Detecting Historical Revisionism in Large Language Models por Ortu, Francesco, Yook, Joeun, Pandey, Punya Syon, Schölkopf, Bernhard, Cazzaniga, Alberto, Mihalcea, Rada, Jin, Zhijing

Obter o texto integral
Obter o texto integral

Are LLMs Good Safety Agents or a Propaganda Engine? por Yadav, Neemesh, Ortu, Francesco, Liu, Jiarui, Yook, Joeun, Schölkopf, Bernhard, Mihalcea, Rada, Cazzaniga, Alberto, Jin, Zhijing

Obter o texto integral
Obter o texto integral

The Narrow Gate: Localized Image-Text Communication in Native Multimodal Models por Serra, Alessandro Pietro, Ortu, Francesco, Panizon, Emanuele, Valeriani, Lucrezia, Basile, Lorenzo, Ansuini, Alessio, Doimo, Diego, Cazzaniga, Alberto

Obter o texto integral
Obter o texto integral

Language Model Alignment in Multilingual Trolley Problems por Jin, Zhijing, Kleiman-Weiner, Max, Piatti, Giorgio, Levine, Sydney, Liu, Jiarui, Gonzalez, Fernando, Ortu, Francesco, Strausz, András, Sachan, Mrinmaya, Mihalcea, Rada, Choi, Yejin, Schölkopf, Bernhard

Obter o texto integral
Obter o texto integral