1 citations · 1 across the 4 of their papers we have counts for
7 papers
Probing and Steering for Safety-Relevant Behaviours in Large Language Models
Nimun Bajwa, Massimo Poesio
Activation probes are computed directions in a language model's residual stream, used both to detect safety-relevant behaviours and, by adding their direction back into the stream,…
Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX
Nan Li, Albert Gatt, Massimo Poesio
In collaborative tasks with asymmetric information, participants coordinate their understanding through interaction. We ask whether gaze provides evidence about grounding across tw…
Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue
Nan Li, Albert Gatt, Massimo Poesio
In collaborative dialogue, shared perception does not guarantee shared interpretation. Mutual understanding must be established through interaction. We investigate whether vision-l…
Grounded Misunderstandings in Asymmetric Dialogue: A Perspectivist Annotation Scheme for MapTask
Nan Li, Albert Gatt, Massimo Poesio
Collaborative dialogue relies on participants incrementally establishing common ground, yet in asymmetric settings they may believe they agree while referring to different entities…
Understanding The Effect Of Temperature On Alignment With Human Opinions
Maja Pavlovic, Massimo Poesio
With the increasing capabilities of LLMs, recent studies focus on understanding whose opinions are represented by them and how to effectively extract aligned opinion distributions.…
Integrating knowledge bases to improve coreference and bridging resolution for the chemical domain
Pengcheng Lu, Massimo Poesio
Resolving coreference and bridging relations in chemical patents is important for better understanding the precise chemical process, where chemical domain knowledge is very critica…
Extending Activation Steering to Broad Skills and Multiple Behaviours
Teun van der Weij, Massimo Poesio, Nandi Schoots
Current large language models have dangerous capabilities, which are likely to become more problematic in the future. Activation steering techniques can be used to reduce risks fro…