model alignment

URPO: A Unified Reward & Policy Optimization Framework for Large Language Models AAAI 2026 When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models AAAI 2026 2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision NAACL 2025 Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent EMNLP 2025 Advantage-Guided Distillation for Preference Alignment in Small Language Models ICLR 2025 A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users EMNLP 2025 AI Sandbagging: Language Models can Strategically Underperform on Evaluations ICLR 2025 Aligning Black-box Language Models with Human Judgments NAACL 2025 Aligning to What? Limits to RLHF Based Alignment NAACL 2025 (Almost) Free Modality Stitching of Foundation Models EMNLP 2025 Amuro & Char: Analyzing the Relationship between Pre-Training and Fine-Tuning of Large Language Models NAACL 2025 Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts EMNLP 2025 Anyprefer: An Agentic Framework for Preference Data Synthesis ICLR 2025 ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning ACL 2025 A transfer learning framework for weak to strong generalization ICLR 2025 Backtracking Improves Generation Safety ICLR 2025 Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court Cases ACL 2025 Beyond Binary Preferences: Semi-Online Label-Free GRACE-KTO with Group-Wise Adaptive Calibration for High-Quality Long-Text Generation EMNLP 2025 Beyond single neurons: population response geometry in digital twins of mouse visual cortex ICLR 2025 Binary Classifier Optimization for Large Language Model Alignment ACL 2025 Bridge-Coder: Transferring Model Capabilities from High-Resource to Low-Resource Programming Language ACL 2025 Call for Rigor in Reporting Quality of Instruction Tuning Data ACL 2025 Causally Motivated Sycophancy Mitigation for Large Language Models ICLR 2025 Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch ACL 2025 Collab: Controlled Decoding using Mixture of Agents for LLM Alignment ICLR 2025