10 papers
Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
Nicolás Astorga, Nabeel Seedat, Mihaela van der Schaar
Verifiable reward training has improved mathematical and coding reasoning, but these domains capture only part of step-by-step decision making. Many real-world tasks require findin…
Influence-Guided Symbolic Regression: Scientific Discovery via LLM-Driven Equation Search with Granular Feedback
Evgeny S. Saveliev, Samuel Holt, Nabeel Seedat +3
Large Language Models (LLMs) offer a promising avenue for scientific discovery, yet their application to symbolic regression is often constrained by inefficient search strategies a…
Scales++: Compute Efficient Evaluation Subset Selection with Cognitive Scales Embeddings
Andrew M. Bean, Nabeel Seedat, Shengzhuang Chen +1
The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks necessitates the creation of small yet representative data subsets (i.e., tiny benchmark…
To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands
Fangyi Yu, Nabeel Seedat, Jonathan Richard Schwarz +1
Language models deployed in high-stakes professional settings face conflicting demands from users, institutional authorities, and professional norms. How models act when these dema…
Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification
Yichi Zhang, Nabeel Seedat, Yinpeng Dong +3
As LLM-powered agents have been used for high-stakes decision-making, such as clinical diagnosis, it becomes critical to develop reliable verification of their decisions to facilit…
Towards Human-Guided, Data-Centric LLM Co-Pilots
Evgeny Saveliev, Jiashuo Liu, Nabeel Seedat +2
Machine learning (ML) has the potential to revolutionize various domains, but its adoption is often hindered by the disconnect between the needs of domain experts and translating t…