3 papers
cs.AI2026
VecCISC: Improving Confidence-Informed Self-Consistency with Reasoning Trace Clustering and Candidate Answer Selection
James Petullo, Sonny George, Dylan Cashman +1
A standard technique for scaling inference-time reasoning is Self-Consistency, whereby multiple candidate answers are sampled from an LLM and the most common answer is selected. Mo…
cs.CL2025
Incorporating Token Usage into Prompting Strategy Evaluation
Chris Sypherd, Sergei Petrov, Sonny George +1
In recent years, large language models have demonstrated remarkable performance across diverse tasks. However, their task effectiveness is heavily dependent on the prompting strate…
cs.CL2024
Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction
Sonny George, Chris Sypherd, Dylan Cashman
Large language model (LLM) agents show promise in an increasing number of domains. In many proposed applications, it is expected that the agent reasons over accumulated experience…