Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection
Yigit Turkmen, Baturalp Buyukates, Melih Bastopcu
Large language models (LLMs) are often ensembled together to improve overall reliability and robustness, but in practice models are strongly correlated. This raises a fundamental q…
cs.LG2026
Queueing-Aware Optimization of Reasoning Tokens for Accuracy-Latency Trade-offs in LLM Servers
Emre Ozbas, Melih Bastopcu
We consider a single large language model (LLM) server that serves a heterogeneous stream of queries belonging to distinct task types. Queries arrive according to a Poisson pro…
cs.LG2025
Balancing Information Accuracy and Response Timeliness in Networked LLMs
Yigit Turkmen, Baturalp Buyukates, Melih Bastopcu
Recent advancements in Large Language Models (LLMs) have transformed many fields including scientific discovery, content generation, biomedical text mining, and educational technol…