{"total":53,"rows":[{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2408.08072","title":"I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm","created":"2024-08-15","cited_by_count":27,"area":null},{"id":"2502.17184","title":"Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2503.11441","title":"D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning","created":"2025-03-14","cited_by_count":21,"area":null},{"id":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","cited_by_count":21,"area":"alignment"},{"id":"2410.15633","title":"GATEAU: Selecting Influential Samples for Long Context Alignment","created":"2024-10-21","cited_by_count":20,"area":"alignment"},{"id":"2408.02193","title":"CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2410.15225","title":"Chasing Random: Instruction Selection Strategies Fail to Generalize","created":"2024-10-19","cited_by_count":13,"area":null},{"id":"2406.14115","title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models","created":"2024-06-20","cited_by_count":12,"area":"lr"},{"id":"2502.07340","title":"Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering","created":"2025-02-11","cited_by_count":12,"area":"alignment"},{"id":"2502.14050","title":"Diversity-driven Data Selection for Language Model Tuning through Sparse Autoencoder","created":"2025-02-19","cited_by_count":12,"area":"mechinterp"},{"id":"2504.13835","title":"MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space","created":"2025-04-18","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":"2412.01377","title":"Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2510.17847","title":"CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization","created":"2025-10-11","cited_by_count":8,"area":"mllm"},{"id":"2505.17266","title":"Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2508.20916","title":"SageLM: A Multi-aspect and Explainable Large Language Model for Speech Judgement","created":"2025-08-28","cited_by_count":7,"area":null},{"id":"2410.14940","title":"Baichuan Alignment Technical Report","created":"2024-10-19","cited_by_count":6,"area":"alignment"},{"id":"2505.17691","title":"ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2406.17305","title":"Retrieval Augmented Instruction Tuning for Open NER with Large Language Models","created":"2024-06-25","cited_by_count":4,"area":"rag"},{"id":"2504.13227","title":"DIDS: Domain Impact-aware Data Sampling for Large Language Model Training","created":"2025-04-17","cited_by_count":4,"area":null},{"id":"2405.13541","title":"Annotation-Efficient Language Model Alignment via Diverse and Representative Response Texts","created":"2024-05-22","cited_by_count":3,"area":"alignment"},{"id":"2503.00034","title":"MergeIT: From Selection to Merging for Efficient Instruction Tuning","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2504.07288","title":"MDIT: A Model-free Data Interpolation Method for Diverse Instruction Tuning","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2505.05327","title":"RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2505.24768","title":"From Macro to Micro: Probing Dataset Diversity in Language Model Fine-Tuning","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2510.07118","title":"TRIM: Token-wise Attention-Derived Saliency for Data-Efficient Instruction Tuning","created":"2025-10-08","cited_by_count":3,"area":"alignment"},{"id":"2502.18978","title":"Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning","created":"2025-02-26","cited_by_count":2,"area":null},{"id":"2503.11126","title":"MUSS: Multilevel Subset Selection for Relevance and Diversity","created":"2025-03-14","cited_by_count":2,"area":"rag"},{"id":"2512.06678","title":"GradientSpace: Unsupervised Data Clustering for Improved Instruction Tuning","created":"2025-12-07","cited_by_count":2,"area":null},{"id":"2603.04981","title":"Rethinking Representativeness and Diversity in Dynamic Data Selection","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2408.09327","title":"Threshold Filtering Packing for Supervised Fine-Tuning: Training Related Samples within Packs","created":"2024-08-18","cited_by_count":1,"area":null},{"id":"2412.06575","title":"Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2505.12754","title":"ProDS: Preference-oriented Data Selection for Instruction Tuning","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2505.22157","title":"LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.23440","title":"Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation","created":"2025-07-31","cited_by_count":1,"area":null},{"id":"2508.05496","title":"InfiAlign: A Scalable and Sample-Efficient Framework for Aligning LLMs to Enhance Reasoning Capabilities","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2509.01221","title":"DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression","created":"2025-09-01","cited_by_count":1,"area":null},{"id":"2510.13892","title":"The Harder The Better: Maintaining Supervised Fine-tuning Generalization with Less but Harder Data","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2602.13773","title":"On Representation Redundancy in Large-Scale Instruction Tuning Data Selection","created":"2026-02-14","cited_by_count":1,"area":null},{"id":"2603.13790","title":"Aligning the Query Space: Greedy Information Projection for Language Model Data Selection","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2503.15924","title":"Towards Automatic Continual Learning: A Self-Adaptive Framework for Continual Instruction Tuning","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2509.06463","title":"Accelerate Scaling of LLM Finetuning via Quantifying the Coverage and Depth of Instruction Set","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.15549","title":"M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasets","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2510.24425","title":"Comprehensive and Efficient Distillation for Lightweight Sentiment Analysis Models","created":"2025-10-28","cited_by_count":0,"area":"distill"},{"id":"2601.13995","title":"From Tags to Trees: Structuring Fine-Grained Knowledge for Controllable Data Selection in LLM Instruction Tuning","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2603.16483","title":"On the Emotion Understanding of Synthesized Speech","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.09665","title":"Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2606.07690","title":"HARP: Efficient Data Selection for Finetuning Large Language Models","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.11423","title":"ToFu: A White-Box, Token-Efficient Agent Harness for Researchers","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2608.28361","title":"GRACE:Gradient-guided Coreset Selection for LLM Unlearning","created":"2026-08-28","cited_by_count":0,"area":"safety"},{"id":"2609.32484","title":"Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}