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
63 results for “keyword:"representation engineering"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Measure Once, Steer with Many: Context Contamination and Composite Control for Persona Drift in LLMs▼5.8k2.33
[PDF]Steering Language Models Without Contrastive Pairs via Unsupervised Latent Region Matching▼1351.33
[PDF]MetaSteer: Context-Conditioned, Non-linear Steering via Attention-Projection Adaptation▲9.2k2.67
[PDF]A Jailbreak Success Coordinate Outside the Refusal Subspace: Decodable Before Generation, Reachable from the Input▼5.8k2.33
[PDF]Robust Steerability: Closed-Loop Control of Language Model Representations Under Distribution Shift▼4.5k2.67
[PDF]Anchored but Not Protected: When Refusal Erodes During Fine-Tuning, and Whether Holding One Direction Stops It▲13k2.33
[PDF]CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits▼4.5k2.67
[PDF]Fireman against Jody: Causal Counterfactual Mirrors for Auditing Strategic Deception in Language Models▼1.2k1.67
[PDF]One Token Can Be Enough: Bridging Prompting and Activation Steering with Prefix Steering▲5103.00
[PDF]Prompt-Adapted Transport Control: Contextual Tokenwise LLM Behaviour Steering via Flow Matching▼4.5k2.67
[PDF]Construct Before Compose: Preserving Conditional Structure in Representation-Based Bias Mitigation▼1601.50
[PDF]JAM: Controllable and Responsible Text Generation via Causal Reasoning and Latent Vectors Manipulation▼1601.50
[PDF]Training-Induced Reasoning Directions: Uncovering Reusable Structure in Post-Training Reasoning▼5.8k2.33
[PDF]X-OPSD: Culture-Preserving On-Policy Self-Distillation for Cross-Lingual Capability Transfer▼4.3k2.00
[PDF]Representing and Steering a Hypothesized Consciousness Spectrum: Manifold-Guided vs. Linear Directions▼4.3k2.00
[PDF]You Only Pass Once: Answering and Abstaining Together in a Single Forward Pass of a Frozen Language Model▲5.4k3.00
[PDF]Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents▲9.2k2.67
[PDF]Expressing an Emotion Is Not Acting on It: Evaluating Emotion Steering against Random Directions in Static Tasks and Long-Horizon Agents▲6.1k2.00
Withdrawn or desk rejected (7)
[PDF]The Geometry of Sycophancy Breakdown: Dual-State Manifold Pathology and the Physical Limits of Representation SteeringWithdrawn1.33
[PDF]-VLM: Detecting and Correcting Vision-Language Hallucination via Active Representational Perturbation and Residual Spectral GroundingWithdrawn1.33
[PDF]The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language ModelsWithdrawn1.67
[PDF]Defending Large Language Models Against Diverse Jailbreak Attacks via Multi-Concept DetectionWithdrawn1.33