conftrace_

token-level confidence

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

semantic agreement (1) llm cascade (1) deferral mechanism (1) output deferral (1) diffusion large language model (1) guided fine-tuning (1) temporal calibration (1) output reliability (1) large language model (1) bidirectional context (1)

Papers

DecoCal: Decoding with Calibration in Diffusion Large Language Models ACL 2026 GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models ACL 2026 Semantic Agreement Enables Efficient Open-Ended LLM Cascades EMNLP 2025