3 papers
cs.CL2025
Textual Gradients are a Flawed Metaphor for Automatic Prompt Optimization
Daniel Melcer, Qi Chen, Wen-Hao Chiang +3
A well-engineered prompt can increase the performance of large language models; automatic prompt optimization techniques aim to increase performance without requiring human effort…
cs.CL2024
Approximately Aligned Decoding
Daniel Melcer, Sujan Gonugondla, Pramuditha Perera +7
It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation to re-sample after a rejectio…
cs.PL2024
Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars
Daniel Melcer, Nathan Fulton, Sanjay Krishna Gouda +1
Large Language Models are powerful tools for program synthesis and advanced auto-completion, but come with no guarantee that their output code is syntactically correct. This paper…