Filtered to natural language processing · clear filter
This paper introduces a framework to audit system prompts in AI applications, examining how developers design and use these prompts to govern the behaviors of foundation models. Practitioners should care because the lack of transparency and accountability in system prompts can erode trust in AI systems.
This paper investigates how AI-assisted coding assistants can better understand and respond to users' ambiguous coding requests by leveraging their past experiences. A practitioner might care about developing more effective coding assistants that can reduce the need for repeated clarification.
This paper introduces a new framework called SpecFirst that helps AI agents construct software programs from scratch by first eliciting a clear behavioral specification from natural-language documentation and an executable binary. Practitioners might care about this approach because it can improve the efficiency and accuracy of program synthesis.
This paper introduces a new approach to agentic speech recognition that uses a memory to help correct mistakes and improve accuracy. By limiting the corrections made, the system can avoid over-correcting and improve performance on challenging tasks.
This paper creates a systematic framework for understanding memory in large language models, helping researchers design more scalable and adaptive language models. Practitioners might care because it provides a unified perspective on memory mechanisms, making it easier to evaluate and improve language model performance.
This paper develops a method to clean up noisy signals in reasoning traces of large models to improve detection of hallucinations, which are false answers produced by models. Practitioners might care about this because it could lead to more accurate models that produce reliable answers.