{"total":18,"rows":[{"id":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137,"area":null},{"id":"2510.16727","title":"Beacon: Single-Turn Diagnosis and Mitigation of Latent Sycophancy in Large Language Models","created":"2025-10-19","cited_by_count":3,"area":null},{"id":"2604.10733","title":"Too Nice to Tell the Truth: Quantifying Agreeableness-Driven Sycophancy in Role-Playing Language Models","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2605.10379","title":"Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2608.09538","title":"TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability","created":"2026-08-10","cited_by_count":3,"area":null},{"id":"2605.09314","title":"How LLMs Are Persuaded: A Few Attention Heads, Rerouted","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2605.12120","title":"To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2606.07441","title":"Sycophantic Praise: Evaluating Excessive Praise in Language Models","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2607.23976","title":"This Is a Good Paper, Right? How Tag Questions Affect Sycophancy Across 106 Language Models","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2609.32867","title":"Are You Sure You're Sure? Two Confounds in a Sycophancy Benchmark","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2601.03285","title":"Feedback Indices to Evaluate LLM Responses to Rebuttals for Multiple Choice Type Questions","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2606.30219","title":"EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.10526","title":"Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2608.11528","title":"Group Alignment-Induced Sycophancy: A Two-Sided Evaluation of Steerable Pluralistic Alignment","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2609.13841","title":"Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship Advice","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.23939","title":"XYEval: Agents say yes to bad advice","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.35606","title":"TCSAlgBench: Benchmarking Automated Proving for Research-Level Theoretical Computer Science","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.06668","title":"Language models can notice an impossible engineering problem yet still report it as solved","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}