2 papers
cs.CL2024
GNOME: Generating Negotiations through Open-Domain Mapping of Exchanges
Darshan Deshpande, Shambhavi Sinha, Anirudh Ravi Kumar +2
Language Models have previously shown strong negotiation capabilities in closed domains where the negotiation strategy prediction scope is constrained to a specific setup. In this…
cs.CL2024
QCQA: Quality and Capacity-aware grouped Query Attention
Vinay Joshi, Prashant Laddha, Shambhavi Sinha +2
Excessive memory requirements of key and value features (KV-cache) present significant challenges in the autoregressive inference of large language models (LLMs), restricting both…