AI RESEARCH
Task-Awareness Improves LLM Generations and Uncertainty
arXiv CS.LG
•
ArXi:2601.21500v2 Announce Type: replace In many applications of LLMs, natural language responses often have an underlying structure such as representing discrete labels, numerical values, or graphs. Yet, existing decoding and uncertainty estimation methods operate only in language space and largely disregard structural information. We address this by modeling LLM outputs directly in a task-dependent latent structure. By equipping this structure with a dissimilarity measure, we can compute Bayes-optimal responses.