9 papers
PALMs: Using Multi Construct-Grounded Rationales for Modeling Population Preferences in LLMs
Priyanka Dey, Brihi Joshi, Preyashi Poddar +2
Large language models are being extensively used to simulate individual user behavior, yet faithfully representing a population requires capturing the systematic variation in value…
QuantiBias: Benchmarking Quantization-Induced Bias in LLMs
Emilio Ferrara
Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safet…
RLHF May Not Reflect Genuine Preferences
Bijean Ghafouri, Eun Cheol Choi, Priyanka Dey +1
Reinforcement Learning from Human Feedback (RLHF) assumes that annotation responses reflect genuine human preferences. They often do not. Behavioral scientists have documented for…
Psychological Steering of Large Language Models
Leonardo Blas, Robin Jia, Emilio Ferrara
Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is converging on additive residual-st…
MOSAIC: Unveiling the Moral, Social and Individual Dimensions of Large Language Models
Erica Coppolillo, Emilio Ferrara
Large Language Models (LLMs) are increasingly deployed in sensitive applications including psychological support, healthcare, and high-stakes decision-making. This expansion has mo…
GRAVITY: A Framework for Personalized Text Generation via Profile-Grounded Synthetic Preferences
Priyanka Dey, Daniele Rosa, Wenqing Zheng +3
Personalization in LLMs often relies on costly human feedback or interaction logs, limiting scalability and neglecting deeper user attributes. To reduce the reliance on human annot…