{"total":15,"rows":[{"id":"2405.09719","title":"Spectral Editing of Activations for Large Language Model Alignment","created":"2024-05-15","cited_by_count":56,"area":"alignment"},{"id":"2210.07440","title":"InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":7,"area":"alignment"},{"id":"2211.05750","title":"Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control","created":"2022-11-10","cited_by_count":6,"area":"alignment"},{"id":"2508.20766","title":"Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection","created":"2025-08-28","cited_by_count":5,"area":"alignment"},{"id":"2505.19327","title":"Paying Alignment Tax with Contrastive Learning","created":"2025-05-25","cited_by_count":3,"area":"alignment"},{"id":"2603.03291","title":"One Bias After Another: Mechanistic Reward Shaping and Persistent Biases in Language Reward Models","created":"2026-02-06","cited_by_count":3,"area":"alignment"},{"id":"2607.21356","title":"Emergent Misalignment Recruits a Pre-existing Persona Subspace","created":"2026-07-23","cited_by_count":3,"area":"alignment"},{"id":"2509.02133","title":"AMBEDKAR-A Multi-level Bias Elimination through a Decoding Approach with Knowledge Augmentation for Robust Constitutional Alignment of Language Models","created":"2025-09-02","cited_by_count":2,"area":"alignment"},{"id":"2601.08489","title":"Surgical Refusal Ablation: Disentangling Safety from Intelligence via Concept-Guided Spectral Cleaning","created":"2026-01-13","cited_by_count":2,"area":"alignment"},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2502.19463","title":"Hedging and Non-Affirmation: Quantifying LLM Alignment on Questions of Human Rights","created":"2025-02-26","cited_by_count":1,"area":"alignment"},{"id":"2605.16600","title":"Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight space","created":"2026-05-15","cited_by_count":1,"area":"alignment"},{"id":"2607.12985","title":"Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs","created":"2026-07-14","cited_by_count":1,"area":"alignment"},{"id":"2603.04822","title":"VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment","created":"2026-03-05","cited_by_count":0,"area":"alignment"},{"id":"2609.09793","title":"How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoE","created":"2026-09-09","cited_by_count":0,"area":"alignment"}],"next_cursor":null}