{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2311.07911","title":"Instruction-Following Evaluation for Large Language Models","created":"2023-11-14","cited_by_count":1228},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2404.13208","title":"The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions","created":"2024-04-19","cited_by_count":493},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2402.06363","title":"StruQ: Defending Against Prompt Injection with Structured Queries","created":"2024-02-09","cited_by_count":375},{"id":"2310.07641","title":"Evaluating Large Language Models at Evaluating Instruction Following","created":"2023-10-11","cited_by_count":302},{"id":"2406.18510","title":"WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models","created":"2024-06-26","cited_by_count":223},{"id":"2409.05907","title":"Programming Refusal with Conditional Activation Steering","created":"2024-09-06","cited_by_count":206},{"id":"2307.09702","title":"Efficient Guided Generation for Large Language Models","created":"2023-07-19","cited_by_count":200},{"id":"2410.12877","title":"Improving Instruction-Following in Language Models through Activation Steering","created":"2024-10-15","cited_by_count":160},{"id":"2407.03978","title":"Benchmarking Complex Instruction-Following with Multiple Constraints Composition","created":"2024-07-04","cited_by_count":152},{"id":"2401.03601","title":"InFoBench: Evaluating Instruction Following Ability in Large Language Models","created":"2024-01-07","cited_by_count":135},{"id":"2303.16755","title":"Training Language Models with Language Feedback at Scale","created":"2023-03-28","cited_by_count":128},{"id":"2305.06474","title":"Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction","created":"2023-05-10","cited_by_count":116},{"id":"2407.12043","title":"The Art of Saying No: Contextual Noncompliance in Language Models","created":"2024-07-02","cited_by_count":105},{"id":"2403.06988","title":"Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation","created":"2024-02-07","cited_by_count":101},{"id":"2406.16008","title":"Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilization","created":"2024-06-23","cited_by_count":101},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91},{"id":"2402.18667","title":"FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability","created":"2024-02-28","cited_by_count":80},{"id":"2309.09117","title":"Contrastive Decoding Improves Reasoning in Large Language Models","created":"2023-09-17","cited_by_count":74},{"id":"2310.14542","title":"Evaluating Large Language Models on Controlled Generation Tasks","created":"2023-10-23","cited_by_count":73},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62},{"id":"2312.10113","title":"Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation","created":"2023-12-15","cited_by_count":62},{"id":"2311.10054","title":"When \"A Helpful Assistant\" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models","created":"2023-11-16","cited_by_count":53},{"id":"2402.10962","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","created":"2024-02-13","cited_by_count":53},{"id":"2407.00121","title":"Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Tasks","created":"2024-06-27","cited_by_count":52},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43},{"id":"2403.05767","title":"Extending Activation Steering to Broad Skills and Multiple Behaviours","created":"2024-03-09","cited_by_count":40},{"id":"2301.08110","title":"AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation","created":"2023-01-19","cited_by_count":31},{"id":"2410.14516","title":"Do LLMs \"know\" internally when they follow instructions?","created":"2024-10-18","cited_by_count":26},{"id":"2409.03621","title":"Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers","created":"2024-09-05","cited_by_count":25},{"id":"2405.01768","title":"Context Steering: Controllable Personalization at Inference Time","created":"2024-05-02","cited_by_count":22},{"id":"2309.10687","title":"EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning","created":"2023-09-16","cited_by_count":13},{"id":"2101.00371","title":"On-the-Fly Attention Modulation for Neural Generation","created":"2021-01-02","cited_by_count":12},{"id":"2402.13463","title":"RefuteBench: Evaluating Refuting Instruction-Following for Large Language Models","created":"2024-02-21","cited_by_count":11},{"id":"2406.17095","title":"Attention Instruction: Amplifying Attention in the Middle via Prompting","created":"2024-06-24","cited_by_count":6},{"id":"2502.09647","title":"Unveiling Simplicities of Attention: Adaptive Long-Context Head Identification","created":"2025-02-11","cited_by_count":5}],"next_cursor":null}