Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
FORGE: Verification-Gated Behavioral Repair for Generative Language Models
Hsin-Ling Hsu, Min-Yu Chen, Nai-Chia Chen +3
Generative large language models (LLMs) inherit undesirable behaviors from pre-training, including demographic bias and toxic generation, that often emerge only after deployment an…
cs.CL2026
Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
Xin Su, Dawid Majchrowski, Fangyuan Yu +5
Large Language Model (LLM) generation remains expensive because autoregressive decoding calls the model once for each new token. Speculative decoding reduces this cost by drafting…