Large Language Models

SELECting over Tokens: Curating Pre-training Data at Scale via Token Classification ACL 2026 Selective Knowledge Distillation: Fusing LLM Semantic Strengths with DNN Efficiency for Binary Code Similarity Detection ACL 2026 Selective Span-Level Unlearning for Large Language Models ACL 2026 Select Less, Reason More: Prioritizing Evidence Purity for Video Reasoning CVPR 2026 Self-Consistency for LLM-Based Motion Trajectory Generation and Verification CVPR 2026 Self-Reflective Generation at Test Time ACL 2026 Self-SoftCoT: A Self-Consistent Framework via Position-Aware Latent Space Reinforcement Learning ACL 2026 Semantic-Aware Logical Reasoning via a Semiotic Framework ACL 2026 Semantic Self-Distillation for Language Model Uncertainty UAI 2026 SemEval-2026 Task 11: Disentangling Content and Formal Reasoning in Large Language Models SemEval 2026 SemEval-2026 Task 4: Narrative Story Similarity and Narrative Representation Learning SemEval 2026 SemEval-2026 Task 6: CLARITY – Unmasking Political Question Evasions SemEval 2026 Sense and Sensitivity: Examining the Influence of Semantic Recall on Long Context Code Understanding ACL 2026 Sense and Sensitivity: “Reasoning” Models are More Robust, but can Diverge from Human Consensus in a Legal Interpretation Task CoNLL 2026 ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production NSDI 2026 SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory UAI 2026 SFTMix: Elevating Language Model Instruction Tuning with Mixup Recipe ACL 2026 SG-LoRA: Semantic-guided LoRA Parameters Generation CVPR 2026 SGT: Securing Open-Source LLMs Against Malicious Fine-tuning via Safety Guidance Trigger ACL 2026 Shanks: Simultaneous Hearing and Thinking for Spoken Language Models ACL 2026 SHAPE: Stage-aware Hierarchical Advantage via Potential Estimation for LLM Reasoning ACL 2026 SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs ACL 2026 SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models ACL 2026 SHARP: Self-adaptive Harmful Category-aware Prompt Generation for Black-box Jailbreaking ACL 2026 SharVeT: Similarity-aware Parameter Sharing with Vector-based Tuning for Efficient LLM Compression ACL 2026