conftrace_

test-time alignment

9 papers

Explore in graph

Co-occurring keywords

large language model (13587) representation editing (10) language dynamical system (1) model utility (36) speculative decoding (111) speculative sampling (8) knapsack problem (39) activation steering (45) depth completion (82) sparse depth (32)

Papers

On the Rejection Criterion for Proxy-based Test-time Alignment ACL 2026
KAD: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral EACL 2026
LLMdoctor: Token-Level Flow-Guided Preference Optimization for Efficient Test-Time Alignment of Large Language Models AAAI 2026
Calibrating Inference Time Alignment with Sequence-level Risk Accumulation ACL 2026
Pref-CTRL: Preference Driven LLM Alignment using Representation Editing ACL 2026
Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Prior AAAI 2025
Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner EMNLP 2025
Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations EMNLP 2024
Aligning Large Language Models with Representation Editing: A Control Perspective NIPS 2024