{"total":70,"rows":[{"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":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699,"area":null},{"id":"2306.04751","title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","created":"2023-06-07","cited_by_count":408,"area":null},{"id":"2203.13366","title":"Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)","created":"2022-03-24","cited_by_count":402,"area":null},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366,"area":null},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326,"area":null},{"id":"2104.07540","title":"Generating Datasets with Pretrained Language Models","created":"2021-04-15","cited_by_count":193,"area":null},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128,"area":null},{"id":"2203.07281","title":"GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models","created":"2022-03-14","cited_by_count":127,"area":null},{"id":"2304.14402","title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","created":"2023-04-27","cited_by_count":124,"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":"2109.03910","title":"A Recipe For Arbitrary Text Style Transfer with Large Language Models","created":"2021-09-08","cited_by_count":107,"area":null},{"id":"2106.11455","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","created":"2021-06-22","cited_by_count":106,"area":null},{"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":"2104.08646","title":"Competency Problems: On Finding and Removing Artifacts in Language Data","created":"2021-04-17","cited_by_count":91,"area":null},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75,"area":null},{"id":"2311.13240","title":"On the Calibration of Large Language Models and Alignment","created":"2023-11-22","cited_by_count":73,"area":null},{"id":"2307.03025","title":"Style Over Substance: Evaluation Biases for Large Language Models","created":"2023-07-06","cited_by_count":70,"area":null},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69,"area":null},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67,"area":null},{"id":"2408.01122","title":"CFBench: A Comprehensive Constraints-Following Benchmark for LLMs","created":"2024-08-02","cited_by_count":67,"area":null},{"id":"2401.06468","title":"Adapting Large Language Models for Document-Level Machine Translation","created":"2024-01-12","cited_by_count":59,"area":null},{"id":"2205.01703","title":"Improving In-Context Few-Shot Learning via Self-Supervised Training","created":"2022-05-03","cited_by_count":57,"area":null},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46,"area":null},{"id":"2106.01465","title":"Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?","created":"2021-06-02","cited_by_count":46,"area":null},{"id":"2305.14302","title":"VIP5: Towards Multimodal Foundation Models for Recommendation","created":"2023-05-23","cited_by_count":46,"area":null},{"id":"2205.12673","title":"InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning","created":"2022-05-25","cited_by_count":39,"area":null},{"id":"2111.13440","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","created":"2021-11-26","cited_by_count":38,"area":null},{"id":"2105.11905","title":"Exploiting Adapters for Cross-lingual Low-resource Speech Recognition","created":"2021-05-18","cited_by_count":35,"area":null},{"id":"2407.12874","title":"SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning","created":"2024-07-16","cited_by_count":32,"area":null},{"id":"2303.10475","title":"Large Language Model Instruction Following: A Survey of Progresses and Challenges","created":"2023-03-18","cited_by_count":31,"area":null},{"id":"2310.15746","title":"Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation","created":"2023-10-24","cited_by_count":30,"area":null},{"id":"2101.00420","title":"Learning to Generate Task-Specific Adapters from Task Description","created":"2021-01-02","cited_by_count":28,"area":null},{"id":"2212.10315","title":"HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation","created":"2022-12-20","cited_by_count":28,"area":null},{"id":"2310.03269","title":"InstructProtein: Aligning Human and Protein Language via Knowledge Instruction","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2302.08624","title":"InstructABSA: Instruction Learning for Aspect Based Sentiment Analysis","created":"2023-02-16","cited_by_count":23,"area":null},{"id":"2105.07903","title":"Factoring Statutory Reasoning as Language Understanding Challenges","created":"2021-05-17","cited_by_count":20,"area":null},{"id":"2402.13887","title":"Beyond Probabilities: Unveiling the Misalignment in Evaluating Large Language Models","created":"2024-02-21","cited_by_count":19,"area":null},{"id":"2205.08124","title":"When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer Learning","created":"2022-05-17","cited_by_count":17,"area":null},{"id":"2203.09161","title":"How Many Data Samples is an Additional Instruction Worth?","created":"2022-03-17","cited_by_count":16,"area":null},{"id":"2204.07600","title":"In-BoXBART: Get Instructions into Biomedical Multi-Task Learning","created":"2022-04-15","cited_by_count":16,"area":null},{"id":"2302.04030","title":"CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Models","created":"2023-02-08","cited_by_count":16,"area":null},{"id":"2210.09175","title":"Learning Instructions with Unlabeled Data for Zero-Shot Cross-Task Generalization","created":"2022-10-17","cited_by_count":15,"area":null},{"id":"2310.14495","title":"InstructExcel: A Benchmark for Natural Language Instruction in Excel","created":"2023-10-23","cited_by_count":15,"area":null},{"id":"2305.11790","title":"Prompting with Pseudo-Code Instructions","created":"2023-05-19","cited_by_count":14,"area":null},{"id":"2402.10770","title":"How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?","created":"2024-02-16","cited_by_count":13,"area":null},{"id":"2109.08079","title":"Context-NER : Contextual Phrase Generation at Scale","created":"2021-09-16","cited_by_count":11,"area":null},{"id":"2212.10755","title":"JASMINE: Arabic GPT Models for Few-Shot Learning","created":"2022-12-21","cited_by_count":11,"area":null},{"id":"2204.09148","title":"What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment","created":"2022-04-19","cited_by_count":9,"area":null},{"id":"2402.11532","title":"Chain-of-Instructions: Compositional Instruction Tuning on Large Language Models","created":"2024-02-18","cited_by_count":9,"area":null},{"id":"2506.08375","title":"EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2308.03853","title":"CORAL: Expert-Curated medical Oncology Reports to Advance Language Model Inference","created":"2023-08-07","cited_by_count":8,"area":null},{"id":"2310.17784","title":"Data-Centric Financial Large Language Models","created":"2023-10-07","cited_by_count":8,"area":null},{"id":"2402.18609","title":"ICE-SEARCH: A Language Model-Driven Feature Selection Approach","created":"2024-02-28","cited_by_count":8,"area":null},{"id":"2109.03731","title":"Cross-Policy Compliance Detection via Question Answering","created":"2021-09-08","cited_by_count":7,"area":null},{"id":"2307.06869","title":"DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering","created":"2023-07-13","cited_by_count":7,"area":null},{"id":"2501.19264","title":"mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval","created":"2025-01-31","cited_by_count":7,"area":null},{"id":"2203.04806","title":"One-Shot Learning from a Demonstration with Hierarchical Latent Language","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2503.19260","title":"Linguistic Blind Spots of Large Language Models","created":"2025-03-25","cited_by_count":6,"area":null},{"id":"2504.16677","title":"A Post-trainer's Guide to Multilingual Training Data: Uncovering Cross-lingual Transfer Dynamics","created":"2025-04-23","cited_by_count":6,"area":null},{"id":"2406.12382","title":"From Instance Training to Instruction Learning: Task Adapters Generation from Instructions","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2112.08637","title":"Analyzing the Limits of Self-Supervision in Handling Bias in Language","created":"2021-12-16","cited_by_count":2,"area":null},{"id":"2212.09104","title":"LaSQuE: Improved Zero-Shot Classification from Explanations Through Quantifier Modeling and Curriculum Learning","created":"2022-12-18","cited_by_count":2,"area":null},{"id":"2212.10019","title":"When Do Decompositions Help for Machine Reading?","created":"2022-12-20","cited_by_count":2,"area":null},{"id":"2110.00125","title":"Combining Transformers with Natural Language Explanations","created":"2021-09-02","cited_by_count":1,"area":null},{"id":"2203.15754","title":"Evaluating Prompts Across Multiple Choice Tasks In a Zero-Shot Setting","created":"2022-03-29","cited_by_count":1,"area":null},{"id":"2109.13029","title":"Every time I fire a conversational designer, the performance of the dialog system goes down","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2304.06184","title":"LINGO : Visually Debiasing Natural Language Instructions to Support Task Diversity","created":"2023-04-12","cited_by_count":0,"area":null},{"id":"2402.10899","title":"Taxonomy-based CheckList for Large Language Model Evaluation","created":"2023-12-15","cited_by_count":0,"area":null},{"id":"2410.02465","title":"Revealing the Inherent Instructability of Pre-Trained Language Models","created":"2024-10-03","cited_by_count":0,"area":null}],"next_cursor":null}