Skip to content
conftrace_

inference-time method

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) contrastive decoding (2) certified mitigation (1) hard negative sample (1) post-training method (1) self-improvement inference (1) attention steering (1) content filtering (1) copyright infringement (1) bloom filter (1)

Papers

Current Advances in LLM Reasoning ACL 2026 Let’s Put Ourselves in Sally’s Shoes: Shoes-of-Others Prefilling Improves Theory of Mind in Large Language Models EACL 2026 Spotlight Your Instructions: Instruction-following with Dynamic Attention Steering EACL 2026 Certified Mitigation of Worst-Case LLM Copyright Infringement EMNLP 2025 Regularized Contrastive Decoding with Hard Negative Samples for LLM Hallucination Mitigation EMNLP 2025 SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully EMNLP 2024