5 papers
Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
Andrew Klearman, Radu Revutchi, Rohin Garg +3
Retrieval quality is the primary bottleneck for accuracy and robustness in retrieval-augmented generation (RAG). Current evaluation relies on heuristically constructed query sets,…
LHAW: Controllable Underspecification for Long-Horizon Tasks
George Pu, Michael S. Lee, Udari Madhushani Sehwag +6
Long-horizon workflow agents that operate effectively over extended periods are essential for truly autonomous systems. Their reliable execution critically depends on the ability t…
VeRO: A Harness for Agents to Optimize Agents
Varun Ursekar, Apaar Shanker, Veronica Chatrath +2
An important emerging application of coding agents is agent harness optimization: the iterative improvement of a target agent by editing and evaluating its code. Despite its releva…
Assessing Robustness to Spurious Correlations in Post-Training Language Models
Julia Shuieh, Prasann Singhal, Apaar Shanker +3
Supervised and preference-based fine-tuning techniques have become popular for aligning large language models (LLMs) with user intent and correctness criteria. However, real-world…
Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs
Yung-Chieh Chan, George Pu, Apaar Shanker +4
As large language models (LLMs) are applied to more use cases, creating high quality, task-specific datasets for fine-tuning becomes a bottleneck for model improvement. Using high…