Showing cs.AIShow all
2 papers · 1 filter
cs.AI2025
Synthetic Error Injection Fails to Elicit Self-Correction In Language Models
David X. Wu, Shreyas Kapur, Anant Sahai +1
Reinforcement learning has become the dominant paradigm for eliciting reasoning and self-correction capabilities in large language models, but its computational expense motivates e…
cs.AI2024
Diffusion On Syntax Trees For Program Synthesis
Shreyas Kapur, Erik Jenner, Stuart Russell
Large language models generate code one token at a time. Their autoregressive generation process lacks the feedback of observing the program's output. Training LLMs to suggest edit…