{"total":61,"rows":[{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2602.11865","title":"Intelligent AI Delegation","created":"2026-02-12","cited_by_count":18,"area":null},{"id":"2509.18052","title":"The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2607.28802","title":"Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures","created":"2026-07-30","cited_by_count":10,"area":null},{"id":"2507.17951","title":"Are LLM Belief Updates Consistent with Bayes' Theorem?","created":"2025-07-23","cited_by_count":9,"area":null},{"id":"2509.00591","title":"Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness","created":"2025-08-30","cited_by_count":9,"area":null},{"id":"2509.04373","title":"Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biases","created":"2025-09-04","cited_by_count":8,"area":null},{"id":"2602.23163","title":"A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2605.26438","title":"LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness","created":"2026-04-08","cited_by_count":4,"area":null},{"id":"2605.28591","title":"Models That Know How Evaluations Are Designed Score Safer","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2606.02211","title":"Consistency Training while Mitigating Obfuscation via Rate Matching","created":"2026-06-01","cited_by_count":4,"area":null},{"id":"2605.23055","title":"Decomposing and Measuring Evaluation Awareness","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2606.11063","title":"CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs","created":"2026-06-09","cited_by_count":3,"area":null},{"id":"2606.23583","title":"Evaluation Awareness Is Not One Capability: Evidence from Open Language Models","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2507.08027","title":"\"Amazing, They All Lean Left\" -- Analyzing the Political Temperaments of Current LLMs","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2607.20436","title":"Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2607.28934","title":"FairFund-Bench: Evaluating Distributive Bias in LLM Resource Allocation","created":"2026-07-31","cited_by_count":2,"area":null},{"id":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2508.11534","title":"Speciesism in AI: Evaluating Discrimination Against Animals in Large Language Models","created":"2025-08-15","cited_by_count":1,"area":null},{"id":"2603.11413","title":"Evaluation format, not model capability, drives measured triage failure in the assessment of consumer health AI","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.13307","title":"PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.29729","title":"Realistic honeypot evaluations for scheming propensity","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.06286","title":"LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.12429","title":"Muse Spark Safety & Preparedness Report","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.01567","title":"Scaling Trends for Lie Detector Oversight in Preference Learning","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.14399","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2608.10703","title":"Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.21766","title":"Evaluation Awareness in Language Models: Representation, Verbalization, and Control","created":"2026-08-22","cited_by_count":1,"area":null},{"id":"2510.04302","title":"When Guessing is Rewarded: Rethinking Language Model Evaluation with Distributional Uncertainty Scoring","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2602.08449","title":"When Evaluation Becomes a Side Channel: Regime Leakage and Structural Mitigations for Alignment Assessment","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.15457","title":"Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.13301","title":"Honeypot Protocol","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.24966","title":"Risk Reporting for Developers' Internal AI Model Use","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.23420","title":"Naturalistic measure of social norms alignment","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2606.07631","title":"Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.08629","title":"Sycophancy Towards Researchers Drives Performative Misalignment","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.28863","title":"Defeat Devices in AI Systems","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2606.31644","title":"Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.23927","title":"Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2607.24758","title":"Do Models Fake Alignment Without Clear Consequences?","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.25891","title":"Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.11008","title":"Templated or fully synthetic? Prompt construction as a confound in measuring LLM political stance beyond writing assistance","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.11513","title":"Do Influence Tactics Matter? Investigating Prompt Framing Effects in LLM Code Generation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.13329","title":"A Probe Direction Is a Property of Its Prompt","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.27340","title":"Not All Eval-Awareness Is Equal: Capabilities Framing Predicts Compliance","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.31105","title":"BLOOM-WILT: Logit Tilting for Behaviour Elicitation in Automated LLM Auditing","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01611","title":"EvalDetectBench: A Benchmark for Measuring Evaluation Awareness in Frontier Language Models","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2609.04444","title":"HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.09048","title":"The Audit Decides the Verdict: Instrument Effects Rival Demographic Bias in LLM Decision Audits","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.20408","title":"Xeno-Interpretability: Investigating the Alien Minds of LLMs","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.22102","title":"When Who You Are Can Change the Code You Get: A Study of Persona-Induced Bias in LLM Code Generation","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.22119","title":"Evaluation Awareness Shifts from Format to Context with Model Scale","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.36316","title":"Training LLMs to Verbalize Evaluation Awareness","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.38262","title":"When Does Randomized Oversight Align AI Agents That Can Conceal?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.06174","title":"Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.10506","title":"Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language Models","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.15634","title":"Big-Big-SycoBench: A Benchmark to Detect Sycophancy Through Model Responses to Valid vs. Invalid Arguments","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16280","title":"agent-risk: Risk Assessment for Changes to AI Agents","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}