NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
1,056 results for “keyword:"alignment"” in ICLR 2027. 253 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Safety Fragility Is a Routing Problem: The Attention Bottleneck Between Harm Detection and Refusal▲1.9k3.67
[PDF]From Behavior to Mechanism: Tracing Divergent Response Modes in Frontier Language Models▼1361.33
[PDF]Alignment Strength Is Not Enough: Backward Influence Allocation in Heterogeneous Multimodal Learning▲9.2k2.67
[PDF]RA-MoE: Routing-Aligned Fine-Tuning for Multilingual Adaptation of Mixture-of-Experts Models▼4.5k2.67
[PDF]Flattening the Connectome Spectrum: A Spectral Filter for FC Induces a Pretraining Target for fMRI Encoders▼4.5k2.67
[PDF]LLM-SemanticLAN: Anchored Public Latent Communication via KV Caches across Heterogeneous Large Language Models▲3.0k2.33
[PDF]Precision Inverse Folding: From Low-Order Mutant Measurements to Higher-Order Variant Prioritization▼1.3k1.75
[PDF]Placebo Audits Quantify Audit-Specific Acceptance under Adaptive Reuse of Verifier Tests▼5.8k2.33
[PDF]TransMap: Metric Embedding of Gene Relational Structures for Image-Native Single-Cell Learning▼5.9k2.50
[PDF]Reasoning Against Alignment: How Viewpoint Processing Destabilizes Safety Boundaries in Aligned LLMs▼1.2k1.67
[PDF]Anchored but Not Protected: When Refusal Erodes During Fine-Tuning, and Whether Holding One Direction Stops It▲13k2.33
[PDF]First-Order In-Context Shapley: Scalable Data Auditing for LLM Alignment and Evaluation▼5.8k2.33
[PDF]PersonaBias: Personalized Chain-of-Thought Optimization for Mitigating Personalized Bias in Large Language Models▼5.8k2.33
[PDF]Similarity Is Not Functional Alignment: What Time-Series–Language Alignment Must Establish▼5.8k2.33
[PDF]Semantic-REACT: Temporally Grounded Linguistic Conditioning for Multiple Appropriate Facial Reaction Generation▼1.2k1.67
[PDF]The Multilingual Alignment Paradox: Preference Conflict Hurts Alignment but Prevents Language Collapse▼4.3k2.00
[PDF]Mitigating Hidden Undesirable Behaviors from LLM Fine-Tuning via Consensus Distillation▲11k2.00
[PDF]Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics▲5103.00
[PDF]Asymptotically Optimal Quantizer-Guided Sinkhorn Alignment for Mitigating Codebook Collapse▲3972.67
Withdrawn or desk rejected (253)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]dREPA: Difficulty-Aware Representation Alignment Accelerates Diffusion TrainingDesk rejected2.00
[PDF]Cross-Domain Micro-Action Learning via Inter-Space Alignment and Prototype CalibrationWithdrawn1.67
[PDF]Beyond Domain Alignment: Anatomically Constrained Unsupervised Adaptation for Optic Nerve Head SegmentationWithdrawn1.00