{"total":289,"rows":[{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418,"area":null},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724,"area":"alignment"},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947,"area":"agents"},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896,"area":null},{"id":"2204.07705","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","created":"2022-04-16","cited_by_count":868,"area":null},{"id":"2210.02414","title":"GLM-130B: An Open Bilingual Pre-trained Model","created":"2022-10-05","cited_by_count":843,"area":null},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"id":"2310.04451","title":"AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models","created":"2023-10-03","cited_by_count":785,"area":"alignment"},{"id":"2303.16199","title":"LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention","created":"2023-03-28","cited_by_count":781,"area":null},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739,"area":null},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686,"area":null},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623,"area":null},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397,"area":null},{"id":"2210.14896","title":"DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models","created":"2022-10-26","cited_by_count":379,"area":"diffusion"},{"id":"2307.13269","title":"LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition","created":"2023-07-25","cited_by_count":364,"area":null},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348,"area":null},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345,"area":null},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326,"area":"mllm"},{"id":"2402.14992","title":"tinyBenchmarks: evaluating LLMs with fewer examples","created":"2024-02-22","cited_by_count":310,"area":null},{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"id":"2209.10063","title":"Generate rather than Retrieve: Large Language Models are Strong Context Generators","created":"2022-09-21","cited_by_count":298,"area":null},{"id":"2303.12528","title":"MEGA: Multilingual Evaluation of Generative AI","created":"2023-03-22","cited_by_count":293,"area":null},{"id":"2210.10723","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","created":"2022-10-19","cited_by_count":277,"area":null},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267,"area":null},{"id":"2305.18752","title":"GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction","created":"2023-05-30","cited_by_count":248,"area":"agents"},{"id":"2212.12017","title":"OPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization","created":"2022-12-22","cited_by_count":236,"area":null},{"id":"2212.04037","title":"Demystifying Prompts in Language Models via Perplexity Estimation","created":"2022-12-08","cited_by_count":216,"area":null},{"id":"2309.08532","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","created":"2023-09-15","cited_by_count":193,"area":null},{"id":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2402.06619","title":"Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning","created":"2024-02-09","cited_by_count":177,"area":null},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2306.14870","title":"Composing Parameter-Efficient Modules with Arithmetic Operations","created":"2023-06-26","cited_by_count":156,"area":null},{"id":"2210.02441","title":"Ask Me Anything: A simple strategy for prompting language models","created":"2022-10-05","cited_by_count":155,"area":null},{"id":"2308.12284","title":"D4: Improving LLM Pretraining via Document De-Duplication and Diversification","created":"2023-08-23","cited_by_count":150,"area":null},{"id":"2211.09102","title":"Prompting PaLM for Translation: Assessing Strategies and Performance","created":"2022-11-16","cited_by_count":145,"area":null},{"id":"2209.11055","title":"Efficient Few-Shot Learning Without Prompts","created":"2022-09-22","cited_by_count":137,"area":null},{"id":"2403.06098","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","created":"2024-03-10","cited_by_count":131,"area":"diffusion"},{"id":"2305.18486","title":"A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets","created":"2023-05-29","cited_by_count":123,"area":null},{"id":"2310.20410","title":"FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models","created":"2023-10-31","cited_by_count":117,"area":null},{"id":"2205.12685","title":"Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations","created":"2022-05-25","cited_by_count":116,"area":null},{"id":"2207.00747","title":"Rationale-Augmented Ensembles in Language Models","created":"2022-07-02","cited_by_count":111,"area":null},{"id":"2212.06094","title":"Prompting Is Programming: A Query Language for Large Language Models","created":"2022-12-12","cited_by_count":110,"area":null},{"id":"2305.14710","title":"Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models","created":"2023-05-24","cited_by_count":110,"area":"safety"},{"id":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107,"area":null},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91,"area":null},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2208.11663","title":"PEER: A Collaborative Language Model","created":"2022-08-24","cited_by_count":86,"area":null},{"id":"2309.08638","title":"Anchor Points: Benchmarking Models with Much Fewer Examples","created":"2023-09-14","cited_by_count":86,"area":null},{"id":"2301.08721","title":"Batch Prompting: Efficient Inference with Large Language Model APIs","created":"2023-01-19","cited_by_count":85,"area":null},{"id":"2302.03202","title":"Exploring the Benefits of Training Expert Language Models over Instruction Tuning","created":"2023-02-07","cited_by_count":80,"area":null},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2209.07661","title":"On the Relation between Sensitivity and Accuracy in In-context Learning","created":"2022-09-16","cited_by_count":72,"area":null},{"id":"2410.02396","title":"Parameter Competition Balancing for Model Merging","created":"2024-10-03","cited_by_count":72,"area":null},{"id":"2211.13892","title":"Complementary Explanations for Effective In-Context Learning","created":"2022-11-25","cited_by_count":71,"area":null},{"id":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71,"area":null},{"id":"2208.07852","title":"Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models","created":"2022-08-16","cited_by_count":70,"area":null},{"id":"2305.09857","title":"CoEdIT: Text Editing by Task-Specific Instruction Tuning","created":"2023-05-17","cited_by_count":68,"area":null},{"id":"2305.14857","title":"BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfer","created":"2023-05-24","cited_by_count":68,"area":null},{"id":"2204.03574","title":"Learning to Compose Soft Prompts for Compositional Zero-Shot Learning","created":"2022-04-07","cited_by_count":67,"area":"mllm"},{"id":"2205.00049","title":"Prompt Consistency for Zero-Shot Task Generalization","created":"2022-04-29","cited_by_count":67,"area":null},{"id":"2210.01296","title":"Recitation-Augmented Language Models","created":"2022-10-04","cited_by_count":65,"area":null},{"id":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62,"area":"safety"},{"id":"2209.12711","title":"Can Large Language Models Truly Understand Prompts? A Case Study with Negated Prompts","created":"2022-09-26","cited_by_count":59,"area":null},{"id":"2212.10378","title":"Data Curation Alone Can Stabilize In-context Learning","created":"2022-12-20","cited_by_count":59,"area":null},{"id":"2303.01911","title":"Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM","created":"2023-03-03","cited_by_count":59,"area":null},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59,"area":null},{"id":"2204.13988","title":"A Taxonomy of Prompt Modifiers for Text-To-Image Generation","created":"2022-04-20","cited_by_count":55,"area":null},{"id":"2212.02199","title":"Legal Prompt Engineering for Multilingual Legal Judgement Prediction","created":"2022-12-05","cited_by_count":55,"area":null},{"id":"2311.00288","title":"Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks","created":"2023-11-01","cited_by_count":55,"area":null},{"id":"2309.02033","title":"Data-Juicer: A One-Stop Data Processing System for Large Language Models","created":"2023-09-05","cited_by_count":52,"area":null},{"id":"2211.11890","title":"TEMPERA: Test-Time Prompting via Reinforcement Learning","created":"2022-11-21","cited_by_count":50,"area":null},{"id":"2212.10539","title":"Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too?","created":"2022-12-20","cited_by_count":49,"area":null},{"id":"2305.11383","title":"Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning","created":"2023-05-19","cited_by_count":49,"area":null},{"id":"2305.14965","title":"Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks","created":"2023-05-24","cited_by_count":49,"area":"safety"},{"id":"2205.00415","title":"Don't Blame the Annotator: Bias Already Starts in the Annotation Instructions","created":"2022-05-01","cited_by_count":47,"area":null},{"id":"2304.08460","title":"LongForm: Effective Instruction Tuning with Reverse Instructions","created":"2023-04-17","cited_by_count":47,"area":null},{"id":"2410.19878","title":"Parameter-Efficient Fine-Tuning in Large Models: A Survey of Methodologies","created":"2024-10-24","cited_by_count":47,"area":null},{"id":"2308.12014","title":"From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models","created":"2023-08-23","cited_by_count":45,"area":"alignment"},{"id":"2306.14321","title":"RobuT: A Systematic Study of Table QA Robustness Against Human-Annotated Adversarial Perturbations","created":"2023-06-25","cited_by_count":43,"area":null},{"id":"2204.07937","title":"Unsupervised Cross-Task Generalization via Retrieval Augmentation","created":"2022-04-17","cited_by_count":42,"area":null},{"id":"2305.09137","title":"Pre-Training to Learn in Context","created":"2023-05-16","cited_by_count":42,"area":null},{"id":"2306.01150","title":"Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning","created":"2023-06-01","cited_by_count":41,"area":"lr"},{"id":"2209.11799","title":"Augmenting Interpretable Models with LLMs during Training","created":"2022-09-23","cited_by_count":38,"area":null},{"id":"2212.09968","title":"On Improving Summarization Factual Consistency from Natural Language Feedback","created":"2022-12-20","cited_by_count":38,"area":"alignment"},{"id":"2305.14327","title":"Dynosaur: A Dynamic Growth Paradigm for Instruction-Tuning Data Curation","created":"2023-05-23","cited_by_count":38,"area":null},{"id":"2211.10681","title":"Decomposed Soft Prompt Guided Fusion Enhancing for Compositional Zero-Shot Learning","created":"2022-11-19","cited_by_count":37,"area":null},{"id":"2206.15076","title":"BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing","created":"2022-06-30","cited_by_count":36,"area":null},{"id":"2312.04339","title":"Merging by Matching Models in Task Parameter Subspaces","created":"2023-12-07","cited_by_count":36,"area":null},{"id":"2212.03813","title":"Robustness of Learning from Task Instructions","created":"2022-12-07","cited_by_count":35,"area":null},{"id":"2304.07987","title":"Chinese Open Instruction Generalist: A Preliminary Release","created":"2023-04-17","cited_by_count":35,"area":null},{"id":"2308.05696","title":"A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment","created":"2023-08-10","cited_by_count":33,"area":"alignment"},{"id":"2401.03003","title":"AST-T5: Structure-Aware Pretraining for Code Generation and Understanding","created":"2024-01-05","cited_by_count":33,"area":null}],"next_cursor":"100"}