{"list":"other","total":51,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2110.02642","title":"Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy","created":"2021-10-06","cited_by_count":394},{"id":"2201.07284","title":"TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data","created":"2022-01-18","cited_by_count":214},{"id":"2308.08241","title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","created":"2023-08-16","cited_by_count":169},{"id":"2402.07319","title":"ODIN: Disentangled Reward Mitigates Hacking in RLHF","created":"2024-02-11","cited_by_count":136},{"id":"2409.12822","title":"Language Models Learn to Mislead Humans via RLHF","created":"2024-09-19","cited_by_count":124},{"id":"2502.18770","title":"Reward Shaping to Mitigate Reward Hacking in RLHF","created":"2025-02-26","cited_by_count":88},{"id":"2305.15778","title":"Automatic Root Cause Analysis via Large Language Models for Cloud Incidents","created":"2023-05-25","cited_by_count":84},{"id":"2406.06144","title":"Language Models Resist Alignment: Evidence From Data Compression","created":"2024-06-10","cited_by_count":53},{"id":"2301.03797","title":"Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models","created":"2023-01-10","cited_by_count":38},{"id":"2402.01140","title":"Root Cause Analysis In Microservice Using Neural Granger Causal Discovery","created":"2024-02-02","cited_by_count":32},{"id":"2508.08712","title":"A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models","created":"2025-08-12","cited_by_count":30},{"id":"2412.11142","title":"AD-LLM: Benchmarking Large Language Models for Anomaly Detection","created":"2024-12-15","cited_by_count":26},{"id":"2209.02500","title":"CausalRCA: Causal Inference based Precise Fine-grained Root Cause Localization for Microservice Applications","created":"2022-09-06","cited_by_count":24},{"id":"2312.11988","title":"Xpert: Empowering Incident Management with Query Recommendations via Large Language Models","created":"2023-12-19","cited_by_count":22},{"id":"2506.18032","title":"Why Do Some Language Models Fake Alignment While Others Don't?","created":"2025-06-22","cited_by_count":20},{"id":"2404.03662","title":"X-lifecycle Learning for Cloud Incident Management using LLMs","created":"2024-02-15","cited_by_count":19},{"id":"2504.06614","title":"AgentFM: Role-Aware Failure Management for Distributed Databases with LLM-Driven Multi-Agents","created":"2025-04-09","cited_by_count":19},{"id":"2507.12472","title":"A Survey of AIOps in the Era of Large Language Models","created":"2025-06-23","cited_by_count":19},{"id":"2504.18776","title":"ThinkFL: Self-Refining Failure Localization for Microservice Systems via Reinforcement Fine-Tuning","created":"2025-04-26","cited_by_count":18},{"id":"2508.07173","title":"Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models","created":"2025-08-10","cited_by_count":18},{"id":"2512.09675","title":"d-TreeRPO: Towards More Reliable Policy Optimization for Diffusion Language Models","created":"2025-12-10","cited_by_count":17},{"id":"2510.01555","title":"Rethinking KL Regularization in RLHF: From Value Estimation to Gradient Optimization","created":"2025-10-02","cited_by_count":14},{"id":"2310.10046","title":"TRANSOM: An Efficient Fault-Tolerant System for Training LLMs","created":"2023-10-16","cited_by_count":13},{"id":"2406.07976","title":"Multivariate Log-based Anomaly Detection for Distributed Database","created":"2024-06-12","cited_by_count":13},{"id":"2508.20370","title":"Adaptive Root Cause Localization for Microservice Systems with Multi-Agent Recursion-of-Thought","created":"2025-08-28","cited_by_count":13},{"id":"2511.01166","title":"MicroRemed: Benchmarking LLMs in Microservices Remediation","created":"2025-11-03","cited_by_count":11},{"id":"2509.24352","title":"Walk the Talk: Is Your Log-based Software Reliability Maintenance System Really Reliable?","created":"2025-09-29","cited_by_count":10},{"id":"2601.02732","title":"Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservices","created":"2026-01-06","cited_by_count":9},{"id":"2409.04834","title":"Reducing Events to Augment Log-based Anomaly Detection Models: An Empirical Study","created":"2024-09-07","cited_by_count":8},{"id":"2509.24364","title":"United We Stand: Towards End-to-End Log-based Fault Diagnosis via Interactive Multi-Task Learning","created":"2025-09-29","cited_by_count":8},{"id":"2601.02736","title":"Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism","created":"2026-01-06","cited_by_count":8},{"id":"2604.10079","title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","created":"2026-04-11","cited_by_count":8},{"id":"2308.11526","title":"Learning Representations on Logs for AIOps","created":"2023-08-18","cited_by_count":6},{"id":"2503.20263","title":"L4: Diagnosing Large-scale LLM Training Failures via Automated Log Analysis","created":"2025-03-26","cited_by_count":6},{"id":"2510.03288","title":"LogAction: Consistent Cross-system Anomaly Detection through Logs via Active Domain Adaptation","created":"2025-09-29","cited_by_count":6},{"id":"2603.21522","title":"Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representation","created":"2026-03-23","cited_by_count":6},{"id":"2510.13694","title":"Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking","created":"2025-10-15","cited_by_count":5},{"id":"2602.10623","title":"Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling","created":"2026-02-11","cited_by_count":5},{"id":"2603.21495","title":"RuntimeSlicer: Towards Generalizable Unified Runtime State Representation for Failure Management","created":"2026-03-23","cited_by_count":5},{"id":"2602.11523","title":"Unifying Stable Optimization and Reference Regularization in RLHF","created":"2026-02-12","cited_by_count":4},{"id":"2604.11094","title":"E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning","created":"2026-04-13","cited_by_count":4},{"id":"2404.01363","title":"AIOps Solutions for Incident Management: Technical Guidelines and A Comprehensive Literature Review","created":"2024-04-01","cited_by_count":3},{"id":"2509.03047","title":"FlashRecovery: Fast and Low-Cost Recovery from Failures for Large-Scale Training of LLMs","created":"2025-09-03","cited_by_count":2},{"id":"2512.22492","title":"Role-Based Fault Tolerance System for LLM RL Post-Training","created":"2025-12-27","cited_by_count":2}],"next_cursor":null}