{"total":77,"rows":[{"id":"2405.09673","title":"LoRA Learns Less and Forgets Less","created":"2024-05-15","cited_by_count":328,"area":null},{"id":"2503.03983","title":"Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities","created":"2025-03-06","cited_by_count":133,"area":"lr"},{"id":"2502.07374","title":"LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters!","created":"2025-02-11","cited_by_count":132,"area":"lr"},{"id":"2410.21228","title":"LoRA vs Full Fine-tuning: An Illusion of Equivalence","created":"2024-10-28","cited_by_count":109,"area":null},{"id":"2402.05123","title":"A Survey on Data Selection for LLM Instruction Tuning","created":"2024-02-04","cited_by_count":77,"area":null},{"id":"2502.04194","title":"The Best Instruction-Tuning Data are Those That Fit","created":"2025-02-06","cited_by_count":52,"area":null},{"id":"2506.18959","title":"From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents","created":"2025-06-23","cited_by_count":51,"area":"lr"},{"id":"2508.01491","title":"The Homogenizing Effect of Large Language Models on Human Expression and Thought","created":"2025-08-02","cited_by_count":35,"area":"lr"},{"id":"2406.16797","title":"Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs","created":"2024-06-24","cited_by_count":31,"area":null},{"id":"2503.02197","title":"ATLaS: Agent Tuning via Learning Critical Steps","created":"2025-03-04","cited_by_count":31,"area":"agents"},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2410.23743","title":"What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective","created":"2024-10-31","cited_by_count":29,"area":"lr"},{"id":"2410.09300","title":"Nudging: Inference-time Alignment of LLMs via Guided Decoding","created":"2024-10-11","cited_by_count":23,"area":null},{"id":"2504.17119","title":"The Rise of Small Language Models in Healthcare: A Comprehensive Survey","created":"2025-04-23","cited_by_count":18,"area":null},{"id":"2404.14122","title":"Fine-Tuning Large Language Models to Translate: Will a Touch of Noisy Data in Misaligned Languages Suffice?","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2509.04484","title":"The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors","created":"2025-08-31","cited_by_count":16,"area":null},{"id":"2506.20963","title":"EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora","created":"2025-06-26","cited_by_count":15,"area":"rag"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2501.14315","title":"Mitigating Forgetting in LLM Fine-Tuning via Low-Perplexity Token Learning","created":"2025-01-24","cited_by_count":14,"area":"synth"},{"id":"2502.12171","title":"GoRA: Gradient-driven Adaptive Low Rank Adaptation","created":"2025-02-13","cited_by_count":12,"area":null},{"id":"2408.08343","title":"API-guided Dataset Synthesis to Finetune Large Code Models","created":"2024-08-15","cited_by_count":11,"area":null},{"id":"2412.15495","title":"TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Use","created":"2024-12-20","cited_by_count":11,"area":"agents"},{"id":"2412.19191","title":"Biology-Instructions: A Dataset and Benchmark for Multi-Omics Sequence Understanding Capability of Large Language Models","created":"2024-12-26","cited_by_count":10,"area":null},{"id":"2406.10773","title":"Quantifying Generative Media Bias with a Corpus of Real-world and Generated News Articles","created":"2024-06-16","cited_by_count":9,"area":null},{"id":"2503.22215","title":"Learning to Instruct for Visual Instruction Tuning","created":"2025-03-28","cited_by_count":8,"area":null},{"id":"2510.01025","title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2512.17910","title":"Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA","created":"2025-11-26","cited_by_count":8,"area":"inference"},{"id":"2406.16783","title":"M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models","created":"2024-06-24","cited_by_count":7,"area":"alignment"},{"id":"2509.16596","title":"Analyzing the Effects of Supervised Fine-Tuning on Model Knowledge from Token and Parameter Levels","created":"2025-09-20","cited_by_count":7,"area":null},{"id":"2510.25758","title":"TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling","created":"2025-10-29","cited_by_count":7,"area":"agents"},{"id":"2406.11474","title":"How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment","created":"2024-06-17","cited_by_count":6,"area":"alignment"},{"id":"2412.19819","title":"ChipAlign: Instruction Alignment in Large Language Models for Chip Design via Geodesic Interpolation","created":"2024-12-15","cited_by_count":6,"area":null},{"id":"2502.04075","title":"From Rational Answers to Emotional Resonance: The Role of Controllable Emotion Generation in Language Models","created":"2025-02-06","cited_by_count":6,"area":null},{"id":"2502.06589","title":"Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training","created":"2025-02-10","cited_by_count":6,"area":"agents"},{"id":"2506.17353","title":"Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs","created":"2025-06-20","cited_by_count":6,"area":"alignment"},{"id":"2410.22944","title":"Focus On This, Not That! Steering LLMs with Adaptive Feature Specification","created":"2024-10-30","cited_by_count":5,"area":null},{"id":"2508.17184","title":"Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models","created":"2025-08-24","cited_by_count":5,"area":"alignment"},{"id":"2512.12677","title":"Fine-Tuning Causal LLMs for Text Classification: Embedding-Based vs. Instruction-Based Approaches","created":"2025-12-14","cited_by_count":5,"area":null},{"id":"2601.13240","title":"KOCO-BENCH: Can Large Language Models Leverage Domain Knowledge in Software Development?","created":"2026-01-19","cited_by_count":5,"area":null},{"id":"2406.12822","title":"Is It Good Data for Multilingual Instruction Tuning or Just Bad Multilingual Evaluation for Large Language Models?","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2503.18460","title":"ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2506.10378","title":"Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","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":"2602.11157","title":"Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety","created":"2025-12-08","cited_by_count":4,"area":"alignment"},{"id":"2412.09614","title":"RAVEL: Rare Concept Generation and Editing via Graph-driven Relational Guidance","created":"2024-12-12","cited_by_count":3,"area":"diffusion"},{"id":"2506.05928","title":"MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models","created":"2025-06-06","cited_by_count":3,"area":"moe"},{"id":"2409.15825","title":"60 Data Points are Sufficient to Fine-Tune LLMs for Question-Answering","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2509.13624","title":"Latent Traits and Cross-Task Transfer: Deconstructing Dataset Interactions in LLM Fine-tuning","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2509.13919","title":"Towards Rationale-Answer Alignment of LVLMs via Self-Rationale Calibration","created":"2025-09-17","cited_by_count":2,"area":"mllm"},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2512.06678","title":"GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2512.17720","title":"Mitigating Forgetting in Low Rank Adaptation","created":"2025-12-19","cited_by_count":2,"area":null},{"id":"2601.07469","title":"Knowledge Distillation for LLM-Based Human Activity Recognition in Homes","created":"2026-01-12","cited_by_count":2,"area":"distill"},{"id":"2601.22708","title":"A Unified Study of LoRA Variants: Taxonomy, Review, Codebase, and Empirical Evaluation","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2604.11838","title":"A Layer-wise Analysis of Supervised Fine-Tuning","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2605.31293","title":"Divergence Decoding: Inference-Time Unlearning via Auxiliary Models","created":"2026-05-29","cited_by_count":2,"area":"safety"},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2407.13419","title":"From Words to Worlds: Compositionality for Cognitive Architectures","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2503.04807","title":"Call for Rigor in Reporting Quality of Instruction Tuning Data","created":"2025-03-04","cited_by_count":1,"area":null},{"id":"2503.08323","title":"Towards Scalable and Cross-Lingual Specialist Language Models for Oncology","created":"2025-03-11","cited_by_count":1,"area":null},{"id":"2506.19563","title":"PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2507.04487","title":"LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimization","created":"2025-07-06","cited_by_count":1,"area":null},{"id":"2602.07930","title":"Patches of Nonlinearity: Instruction Vectors in Large Language Models","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2604.00979","title":"Dual Optimal: Make Your LLM Peer-like with Dignity","created":"2026-04-01","cited_by_count":1,"area":"alignment"},{"id":"2407.21417","title":"Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models","created":"2024-07-31","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},{"id":"2510.01236","title":"GRPO++: Enhancing Dermatological Reasoning under Low Resource Settings","created":"2025-09-23","cited_by_count":0,"area":"lr"},{"id":"2601.22146","title":"FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale","created":"2026-01-29","cited_by_count":0,"area":"synth"},{"id":"2604.09940","title":"New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.20148","title":"Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2606.04160","title":"Decomposing Refusal Steering in Mixture-of-Experts Models","created":"2026-06-02","cited_by_count":0,"area":"alignment"},{"id":"2607.20453","title":"A Knowledge-Injection Framework for Zero-Shot Adaptation of LLMs to Delirium Prediction","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2608.17514","title":"SE-MoLoRA: Shared-Expert LoRA Adapters for Domain-Specific Photographic Assessment","created":"2026-08-18","cited_by_count":0,"area":"mllm"},{"id":"2609.22554","title":"The Ups and Downs of Backprop Weights","created":"2026-09-18","cited_by_count":0,"area":null}],"next_cursor":null}