{"total":15,"rows":[{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2506.00419","title":"Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences","created":"2025-05-31","cited_by_count":10,"area":"alignment"},{"id":"2604.01476","title":"From Rebound to Remedy: Understanding and Mitigating Reward Hacking via Representation Engineering","created":"2026-04-01","cited_by_count":7,"area":"alignment"},{"id":"2509.03647","title":"Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators","created":"2025-09-03","cited_by_count":3,"area":"alignment"},{"id":"2602.16835","title":"NeST: Neuron Selective Tuning for LLM Safety","created":"2026-02-18","cited_by_count":2,"area":"alignment"},{"id":"2603.08104","title":"Invisible Safety Threat: Malicious Finetuning for LLM via Steganography","created":"2026-03-09","cited_by_count":2,"area":"alignment"},{"id":"2603.09692","title":"ActiveUltraFeedback: Efficient Preference Data Generation using Active Learning","created":"2026-03-10","cited_by_count":2,"area":"alignment"},{"id":"2506.11091","title":"Customizing Speech Recognition Model with Large Language Model Feedback","created":"2025-06-05","cited_by_count":1,"area":"alignment"},{"id":"2606.15517","title":"SHARD: Safe and Helpful Alignment via Self-Reframing Distillation","created":"2026-06-14","cited_by_count":0,"area":"alignment"},{"id":"2608.01414","title":"No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks","created":"2026-08-02","cited_by_count":0,"area":"alignment"},{"id":"2608.14629","title":"Inference-Time Mitigation of Adversarial Political Bias in Large Language Models","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2608.26222","title":"NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation","created":"2026-08-26","cited_by_count":0,"area":"alignment"},{"id":"2609.39076","title":"Multi-LLM Collaborative Alignment via Stackelberg Games","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.02568","title":"Mitigating Social Sycophancy via Pluralistic Preference Optimization","created":"2026-10-01","cited_by_count":0,"area":"alignment"}],"next_cursor":null}