{"total":74,"rows":[{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147,"area":null},{"id":"2504.17550","title":"HalluLens: LLM Hallucination Benchmark","created":"2025-04-24","cited_by_count":92,"area":null},{"id":"2404.14387","title":"A Survey on Self-Evolution of Large Language Models","created":"2024-04-22","cited_by_count":91,"area":null},{"id":"2406.06391","title":"Towards Lifelong Learning of Large Language Models: A Survey","created":"2024-06-10","cited_by_count":64,"area":null},{"id":"2405.18653","title":"Recent Advances of Foundation Language Models-based Continual Learning: A Survey","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2407.06089","title":"Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models","created":"2024-07-08","cited_by_count":44,"area":null},{"id":"2407.08699","title":"Mitigating Catastrophic Forgetting in Language Transfer via Model Merging","created":"2024-07-11","cited_by_count":36,"area":null},{"id":"2505.10833","title":"MergeBench: A Benchmark for Merging Domain-Specialized LLMs","created":"2025-05-16","cited_by_count":33,"area":null},{"id":"2412.06712","title":"How to Merge Your Multimodal Models Over Time?","created":"2024-12-09","cited_by_count":23,"area":null},{"id":"2509.21117","title":"TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them","created":"2025-09-25","cited_by_count":20,"area":null},{"id":"2502.08301","title":"Compromising Honesty and Harmlessness in Language Models via Deception Attacks","created":"2025-02-12","cited_by_count":17,"area":null},{"id":"2502.02797","title":"Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting","created":"2025-02-05","cited_by_count":16,"area":null},{"id":"2502.11019","title":"Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2310.02527","title":"CITING: Large Language Models Create Curriculum for Instruction Tuning","created":"2023-10-04","cited_by_count":14,"area":null},{"id":"2407.20999","title":"MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning","created":"2024-07-30","cited_by_count":14,"area":null},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2411.02688","title":"On the Loss of Context-awareness in General Instruction Fine-tuning","created":"2024-11-05","cited_by_count":11,"area":null},{"id":"2505.17496","title":"Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models","created":"2025-05-23","cited_by_count":11,"area":null},{"id":"2510.17776","title":"Mapping Post-Training Forgetting in Language Models at Scale","created":"2025-10-20","cited_by_count":11,"area":null},{"id":"2402.17982","title":"Collaborative decoding of critical tokens for boosting factuality of large language models","created":"2024-02-28","cited_by_count":9,"area":null},{"id":"2503.08796","title":"Robust Multi-Objective Controlled Decoding of Large Language Models","created":"2025-03-11","cited_by_count":9,"area":null},{"id":"2503.13505","title":"Ensemble Learning for Large Language Models in Text and Code Generation: A Survey","created":"2025-03-13","cited_by_count":9,"area":null},{"id":"2506.01901","title":"Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods","created":"2025-06-02","cited_by_count":9,"area":null},{"id":"2411.06824","title":"Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs","created":"2024-11-11","cited_by_count":6,"area":null},{"id":"2605.12484","title":"Learning, Fast and Slow: Towards LLMs That Adapt Continually","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2503.21383","title":"Controlling Large Language Model with Latent Actions","created":"2025-03-27","cited_by_count":5,"area":null},{"id":"2605.07632","title":"Post-training makes large language models less human-like","created":"2026-05-08","cited_by_count":5,"area":null},{"id":"2401.06792","title":"LightHouse: A Survey of AGI Hallucination","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2402.08096","title":"An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning","created":"2024-02-12","cited_by_count":4,"area":null},{"id":"2404.05499","title":"Guiding Large Language Models to Generate Computer-Parsable Content","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2410.12926","title":"DEeR: Deviation Eliminating and Noise Regulating for Privacy-preserving Federated Low-rank Adaptation","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2411.17471","title":"Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2502.19127","title":"Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilization","created":"2025-02-26","cited_by_count":4,"area":null},{"id":"2511.05933","title":"Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2511.11966","title":"On the Entropy Calibration of Language Models","created":"2025-11-15","cited_by_count":4,"area":null},{"id":"2602.15156","title":"Panini: Continual Learning in Token Space via Structured Memory","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2604.19292","title":"Location Not Found: Exposing Implicit Local and Global Biases in Multilingual LLMs","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2603.06610","title":"CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2603.06748","title":"Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2502.12672","title":"Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization","created":"2025-02-18","cited_by_count":2,"area":null},{"id":"2502.15434","title":"Mixup Model Merge: Enhancing Model Merging Performance through Randomized Linear Interpolation","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2507.00163","title":"Prompting as Scientific Inquiry","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2602.00861","title":"Multi-Head Attention Is a Multi-Player Game","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.05164","title":"Position: Capability Control Should be a Separate Goal From Alignment","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2403.07342","title":"Rethinking ASTE: A Minimalist Tagging Scheme Alongside Contrastive Learning","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2411.05209","title":"Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs","created":"2024-11-07","cited_by_count":1,"area":null},{"id":"2503.04834","title":"Extrapolation Merging: Keep Improving With Extrapolation and Merging","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2505.22018","title":"Improving Continual Pre-training Through Seamless Data Packing","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.15932","title":"The Alignment Bottleneck","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.09152","title":"Logits Replay + MoClip: Stabilized, Low-Cost Post-Training with Minimal Forgetting","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.19561","title":"Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2603.00047","title":"What Is the Alignment Tax?","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2605.00610","title":"Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors","created":"2026-05-01","cited_by_count":1,"area":null},{"id":"2605.26442","title":"Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelines","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2606.02252","title":"ResMerge: Residual-based Spectral Merging of Large Language Models","created":"2026-06-01","cited_by_count":1,"area":null},{"id":"2606.18656","title":"The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2608.01743","title":"Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2410.03137","title":"SAG: Style-Aligned Article Generation via Model Collaboration","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2506.23423","title":"TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2508.14118","title":"Hallucinations in medical devices","created":"2025-08-18","cited_by_count":0,"area":null},{"id":"2511.21762","title":"Factors That Support Grounded Responses in LLM Conversations: A Rapid Review","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2604.01538","title":"Countering Catastrophic Forgetting of Large Language Models for Better Instruction Following via Weight-Space Model Merging","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.19087","title":"OLLM: Options-based Large Language Models","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.31025","title":"TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.15734","title":"Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.19346","title":"Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2606.26102","title":"Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2608.15772","title":"Broken Symmetry in LLM Refusal: Answer Release Is More Local Than Refusal Restoration","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.00999","title":"Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.11291","title":"Off-Target Effects of Response-Style Alignment in a Korean 27B Language Model","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.22153","title":"SafeTune: A Unified Faithful Library for Auditing and Repairing Safety Drift in Fine-Tuned LLMs","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.23916","title":"Time-Incremental Continued Pretraining of LLMs: Knowledge Updates Without Catastrophic Forgetting","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.35793","title":"Learning from the Gap Between Pass@K and Pass@1","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}