Search Results for author:
Found 6 papers, 1 papers with code
Can LLMs make trade-offs involving stipulated pain and pleasure states?
Varying the intensity of the pain penalties and pleasure rewards, we found that Claude 3. 5 Sonnet, Command R+, GPT-4o, and GPT-4o mini each demonstrated at least one trade-off in which the majority of responses switched from points-maximisation to pain-minimisation or pleasure-maximisation after a critical threshold of stipulated pain or pleasure intensity is reached.
On the attribution of confidence to large language models
First, our semantic claim is that LLM credence attributions are (at least in general) correctly interpreted literally, as expressing truth-apt beliefs on the part of scientists that purport to describe facts about LLM credences.
LLMs achieve adult human performance on higher-order theory of mind tasks
This paper builds on prior work by introducing a handwritten test suite -- Multi-Order Theory of Mind Q&A -- and using it to compare the performance of five LLMs to a newly gathered adult human benchmark.
A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI
This has led to growing concerns about harms from AI persuasion and how they can be mitigated, highlighting the need for a systematic study of AI persuasion.
Should agentic conversational AI change how we think about ethics? Characterising an interactional ethics centred on respect
With the growing popularity of conversational agents based on large language models (LLMs), we need to ensure their behaviour is ethical and appropriate.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
