{"total":174,"rows":[{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154,"area":"alignment"},{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2305.19860","title":"A Survey on Large Language Models for Recommendation","created":"2023-05-31","cited_by_count":379,"area":null},{"id":"2403.08319","title":"Knowledge Conflicts for LLMs: A Survey","created":"2024-03-13","cited_by_count":283,"area":null},{"id":"2207.13332","title":"RealTime QA: What's the Answer Right Now?","created":"2022-07-27","cited_by_count":244,"area":null},{"id":"2307.12976","title":"Evaluating the Ripple Effects of Knowledge Editing in Language Models","created":"2023-07-24","cited_by_count":242,"area":null},{"id":"2404.16789","title":"Continual Learning of Large Language Models: A Comprehensive Survey","created":"2024-04-25","cited_by_count":234,"area":null},{"id":"2302.03648","title":"Class-Incremental Learning: A Survey","created":"2023-02-07","cited_by_count":209,"area":null},{"id":"2206.04624","title":"Factuality Enhanced Language Models for Open-Ended Text Generation","created":"2022-06-09","cited_by_count":202,"area":null},{"id":"2302.03241","title":"Continual Pre-training of Language Models","created":"2023-02-07","cited_by_count":198,"area":null},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2211.05110","title":"Large Language Models with Controllable Working Memory","created":"2022-11-09","cited_by_count":169,"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":"2308.04014","title":"Continual Pre-Training of Large Language Models: How to (re)warm your model?","created":"2023-08-08","cited_by_count":137,"area":null},{"id":"2202.03829","title":"TimeLMs: Diachronic Language Models from Twitter","created":"2022-02-08","cited_by_count":131,"area":null},{"id":"2403.08763","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","created":"2024-03-13","cited_by_count":127,"area":null},{"id":"2205.11388","title":"StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models","created":"2022-05-23","cited_by_count":126,"area":null},{"id":"2204.14211","title":"TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models","created":"2022-04-29","cited_by_count":119,"area":null},{"id":"2110.08534","title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora","created":"2021-10-16","cited_by_count":115,"area":null},{"id":"2305.14045","title":"The CoT Collection: Improving Zero-shot and Few-shot Learning of Language Models via Chain-of-Thought Fine-Tuning","created":"2023-05-23","cited_by_count":108,"area":"lr"},{"id":"2406.05761","title":"The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language Models","created":"2024-06-09","cited_by_count":93,"area":null},{"id":"2301.12867","title":"Red teaming ChatGPT via Jailbreaking: Bias, Robustness, Reliability and Toxicity","created":"2023-01-30","cited_by_count":89,"area":"safety"},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"area":null},{"id":"2205.09357","title":"Continual Pre-Training Mitigates Forgetting in Language and Vision","created":"2022-05-19","cited_by_count":83,"area":null},{"id":"2501.07278","title":"Lifelong Learning of Large Language Model based Agents: A Roadmap","created":"2025-01-13","cited_by_count":83,"area":"agents"},{"id":"2407.07263","title":"Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Models","created":"2024-07-09","cited_by_count":72,"area":null},{"id":"2203.06311","title":"ELLE: Efficient Lifelong Pre-training for Emerging Data","created":"2022-03-12","cited_by_count":70,"area":null},{"id":"2305.01651","title":"Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge","created":"2023-05-02","cited_by_count":67,"area":null},{"id":"2303.18027","title":"Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations","created":"2023-03-31","cited_by_count":63,"area":null},{"id":"2205.00329","title":"Continual Learning with Foundation Models: An Empirical Study of Latent Replay","created":"2022-04-30","cited_by_count":61,"area":null},{"id":"2205.02832","title":"Entity Cloze By Date: What LMs Know About Unseen Entities","created":"2022-05-05","cited_by_count":55,"area":null},{"id":"2402.12847","title":"Instruction-tuned Language Models are Better Knowledge Learners","created":"2024-02-20","cited_by_count":55,"area":null},{"id":"2305.09955","title":"Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models","created":"2023-05-17","cited_by_count":46,"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":"2305.15076","title":"Meta-Learning Online Adaptation of Language Models","created":"2023-05-24","cited_by_count":43,"area":null},{"id":"2310.16226","title":"TiC-CLIP: Continual Training of CLIP Models","created":"2023-10-24","cited_by_count":38,"area":null},{"id":"2406.18406","title":"IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons","created":"2024-06-26","cited_by_count":38,"area":null},{"id":"2402.18909","title":"AKEW: Assessing Knowledge Editing in the Wild","created":"2024-02-29","cited_by_count":36,"area":null},{"id":"2403.04317","title":"Online Adaptation of Language Models with a Memory of Amortized Contexts","created":"2024-03-07","cited_by_count":35,"area":null},{"id":"2311.08545","title":"Efficient Continual Pre-training for Building Domain Specific Large Language Models","created":"2023-11-14","cited_by_count":34,"area":null},{"id":"2308.11073","title":"Audio-Visual Class-Incremental Learning","created":"2023-08-21","cited_by_count":33,"area":null},{"id":"2310.07343","title":"How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances","created":"2023-10-11","cited_by_count":33,"area":null},{"id":"2304.05510","title":"chatClimate: Grounding Conversational AI in Climate Science","created":"2023-04-11","cited_by_count":32,"area":null},{"id":"2310.16570","title":"Give Me the Facts! A Survey on Factual Knowledge Probing in Pre-trained Language Models","created":"2023-10-25","cited_by_count":32,"area":null},{"id":"2310.11958","title":"Emptying the Ocean with a Spoon: Should We Edit Models?","created":"2023-10-18","cited_by_count":27,"area":null},{"id":"2405.10989","title":"Learnable Privacy Neurons Localization in Language Models","created":"2024-05-16","cited_by_count":27,"area":null},{"id":"2205.12677","title":"Language Anisotropic Cross-Lingual Model Editing","created":"2022-05-25","cited_by_count":26,"area":null},{"id":"2305.16597","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","created":"2023-05-26","cited_by_count":25,"area":null},{"id":"2312.12736","title":"Learning and Forgetting Unsafe Examples in Large Language Models","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2310.07589","title":"Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models","created":"2023-10-11","cited_by_count":23,"area":"rag"},{"id":"2310.07999","title":"LEMON: Lossless model expansion","created":"2023-10-12","cited_by_count":23,"area":"lr"},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2502.11196","title":"How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training","created":"2025-02-16","cited_by_count":23,"area":null},{"id":"2506.05453","title":"MLLM-CL: Continual Learning for Multimodal Large Language Models","created":"2025-06-05","cited_by_count":23,"area":"mllm"},{"id":"2205.02014","title":"On Continual Model Refinement in Out-of-Distribution Data Streams","created":"2022-05-04","cited_by_count":22,"area":null},{"id":"2411.02564","title":"Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models","created":"2024-11-04","cited_by_count":22,"area":"mllm"},{"id":"2302.12297","title":"Dynamic Benchmarking of Masked Language Models on Temporal Concept Drift with Multiple Views","created":"2023-02-23","cited_by_count":21,"area":null},{"id":"2309.05605","title":"Memory Injections: Correcting Multi-Hop Reasoning Failures during Inference in Transformer-Based Language Models","created":"2023-09-11","cited_by_count":21,"area":"lr"},{"id":"2410.00487","title":"Self-Updatable Large Language Models by Integrating Context into Model Parameters","created":"2024-10-01","cited_by_count":21,"area":null},{"id":"2408.03297","title":"KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Models","created":"2024-08-06","cited_by_count":20,"area":"rag"},{"id":"2311.16087","title":"DUnE: Dataset for Unified Editing","created":"2023-11-27","cited_by_count":19,"area":null},{"id":"2411.08324","title":"Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle","created":"2024-11-13","cited_by_count":19,"area":null},{"id":"2305.09144","title":"Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models","created":"2023-05-16","cited_by_count":18,"area":null},{"id":"2311.08106","title":"Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models","created":"2023-11-14","cited_by_count":18,"area":null},{"id":"2305.08702","title":"Recyclable Tuning for Continual Pre-training","created":"2023-05-15","cited_by_count":17,"area":null},{"id":"2406.06326","title":"Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching","created":"2024-06-10","cited_by_count":17,"area":null},{"id":"2603.03818","title":"Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning","created":"2026-03-04","cited_by_count":17,"area":"vla"},{"id":"2410.01380","title":"Knowledge Entropy Decay during Language Model Pretraining Hinders New Knowledge Acquisition","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2407.18743","title":"Towards Effective and Efficient Continual Pre-training of Large Language Models","created":"2024-07-26","cited_by_count":15,"area":null},{"id":"2504.02107","title":"TiC-LM: A Web-Scale Benchmark for Time-Continual LLM Pretraining","created":"2025-04-02","cited_by_count":15,"area":null},{"id":"2406.04496","title":"Time Sensitive Knowledge Editing through Efficient Finetuning","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2502.07760","title":"Scalable Fingerprinting of Large Language Models","created":"2025-02-11","cited_by_count":14,"area":null},{"id":"2306.01904","title":"Overcoming the Stability Gap in Continual Learning","created":"2023-06-02","cited_by_count":13,"area":null},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2412.13582","title":"EvoWiki: Evaluating LLMs on Evolving Knowledge","created":"2024-12-18","cited_by_count":13,"area":null},{"id":"2504.12523","title":"Memorization vs. Reasoning: Updating LLMs with New Knowledge","created":"2025-04-16","cited_by_count":13,"area":"lr"},{"id":"2303.01421","title":"Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction Memory","created":"2023-03-02","cited_by_count":12,"area":null},{"id":"2311.05241","title":"When Meta-Learning Meets Online and Continual Learning: A Survey","created":"2023-11-09","cited_by_count":12,"area":null},{"id":"2303.03628","title":"CoTEVer: Chain of Thought Prompting Annotation Toolkit for Explanation Verification","created":"2023-03-07","cited_by_count":11,"area":"lr"},{"id":"2405.14211","title":"ChronosLex: Time-aware Incremental Training for Temporal Generalization of Legal Classification Tasks","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2406.05606","title":"GrowOVER: How Can LLMs Adapt to Growing Real-World Knowledge?","created":"2024-06-09","cited_by_count":11,"area":null},{"id":"2406.14095","title":"Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2211.02162","title":"Time-aware Prompting for Text Generation","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2502.15680","title":"Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training","created":"2025-02-21","cited_by_count":10,"area":null},{"id":"2505.04416","title":"OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models","created":"2025-05-07","cited_by_count":10,"area":"safety"},{"id":"2311.01200","title":"Continual Learning Under Language Shift","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2402.01865","title":"What Will My Model Forget? Forecasting Forgotten Examples in Language Model Refinement","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2404.00983","title":"Continual Learning for Smart City: A Survey","created":"2024-04-01","cited_by_count":9,"area":null},{"id":"2406.11830","title":"Language Modeling with Editable External Knowledge","created":"2024-06-17","cited_by_count":9,"area":"rag"},{"id":"2408.10210","title":"A Survey on Symbolic Knowledge Distillation of Large Language Models","created":"2024-07-12","cited_by_count":9,"area":"distill"},{"id":"2502.08356","title":"Systematic Knowledge Injection into Large Language Models via Diverse Augmentation for Domain-Specific RAG","created":"2025-02-12","cited_by_count":9,"area":"rag"},{"id":"2310.13024","title":"Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt","created":"2023-10-19","cited_by_count":8,"area":null},{"id":"2406.11275","title":"Self-training Large Language Models through Knowledge Detection","created":"2024-06-17","cited_by_count":8,"area":"synth"},{"id":"2408.07413","title":"Knowledge in Superposition: Unveiling the Failures of Lifelong Knowledge Editing for Large Language Models","created":"2024-08-14","cited_by_count":8,"area":"mechinterp"},{"id":"2410.09870","title":"ChroKnowledge: Unveiling Chronological Knowledge of Language Models in Multiple Domains","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2411.07175","title":"Continual Memorization of Factoids in Language Models","created":"2024-11-11","cited_by_count":8,"area":null},{"id":"2502.12598","title":"Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion","created":"2025-02-18","cited_by_count":8,"area":null},{"id":"2404.18543","title":"Time Machine GPT","created":"2024-04-29","cited_by_count":7,"area":null}],"next_cursor":"100"}