4 papers
Value Entanglement: Conflation Between Different Kinds of Good In (Some) Large Language Models
Seong Hah Cho, Junyi Li, Anna Leshinskaya
Value alignment of Large Language Models (LLMs) requires us to empirically measure these models' actual, acquired representation of value. Among the characteristics of value repres…
The Steganographic Potentials of Language Models
Artem Karpov, Tinuade Adeleke, Seong Hah Cho +1
The potential for large language models (LLMs) to hide messages within plain text (steganography) poses a challenge to detection and thwarting of unaligned AI agents, and undermine…
Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineering
Kenneth J. K. Ong, Lye Jia Jun, Hieu Minh "Jord" Nguyen +2
As Large Language Models (LLMs) gain autonomous capabilities, their coordination in multi-agent settings becomes increasingly important. However, they often struggle with cooperati…
Inducing Human-like Biases in Moral Reasoning Language Models
Artem Karpov, Seong Hah Cho, Austin Meek +3
In this work, we study the alignment (BrainScore) of large language models (LLMs) fine-tuned for moral reasoning on behavioral data and/or brain data of humans performing the same…