{"total":19,"rows":[{"id":"2605.18891","title":"Auditing Reasoning-Trace Memorization Claims after Unlearning with Head-Conditioned Canaries","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2510.11570","title":"Strong but Brittle: Simple Attacks Subvert Reasoning-based Safety Guardrails","created":"2025-10-13","cited_by_count":5,"area":"lr"},{"id":"2511.16940","title":"MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models","created":"2025-11-21","cited_by_count":5,"area":"lr"},{"id":"2511.15169","title":"SafeRBench: Dissecting the Reasoning Safety of Large Language Models","created":"2025-11-19","cited_by_count":4,"area":"lr"},{"id":"2602.03507","title":"FaithRL: Learning to Reason Faithfully through Step-Level Faithfulness Maximization","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2511.12001","title":"Critical or Compliant? The Double-Edged Sword of Reasoning in Chain-of-Thought Explanations","created":"2025-11-15","cited_by_count":3,"area":"lr"},{"id":"2602.02313","title":"Interpreting and Controlling LLM Reasoning through Integrated Policy Gradient","created":"2026-02-02","cited_by_count":3,"area":"lr"},{"id":"2604.14142","title":"From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2510.07697","title":"Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2604.19656","title":"Pause or Fabricate? Training Language Models for Grounded Reasoning","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2601.22735","title":"MM-THEBench: Do Reasoning MLLMs Think Reasonably?","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2606.23404","title":"ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models","created":"2026-06-22","cited_by_count":1,"area":"lr"},{"id":"2602.02295","title":"EvalQReason: A Framework for Step-Level Reasoning Evaluation in Large Language Models","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2604.02230","title":"Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2604.04852","title":"Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework","created":"2026-04-06","cited_by_count":0,"area":"lr"},{"id":"2606.11046","title":"Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning Models","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2608.03745","title":"Risky Business: Measuring The Faithfulness-Safety Tension","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"id":"2610.05472","title":"Hallucination Across the Reasoning Lifecycle: Interface Visibility, Causal Evidence, and Release Control in Large Reasoning Models","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.17607","title":"Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}