← all papers · overview

Forcing Diffuse Distributions Out Of Language Models

Abstract

Despite being trained specifically to follow user instructions, today's instructiontuned language models perform poorly when instructed to produce random outputs. For example, when prompted to pick a number uniformly between one and ten Llama-2-13B-chat disproportionately favors the number five, and when tasked with picking a first name at random, Mistral-7B-Instruct chooses Avery 40 times more of

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).