{"total":56,"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":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2502.15851","title":"Control Illusion: The Failure of Instruction Hierarchies in Large Language Models","created":"2025-02-21","cited_by_count":33,"area":null},{"id":"2311.09731","title":"Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge","created":"2023-11-16","cited_by_count":32,"area":null},{"id":"2510.13900","title":"Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences","created":"2025-10-14","cited_by_count":28,"area":null},{"id":"2502.15576","title":"Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders","created":"2025-02-21","cited_by_count":21,"area":"mechinterp"},{"id":"2405.18915","title":"Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness","created":"2024-05-29","cited_by_count":20,"area":"lr"},{"id":"2410.02331","title":"Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks","created":"2024-10-03","cited_by_count":18,"area":null},{"id":"2403.02246","title":"PHAnToM: Persona-based Prompting Has An Effect on Theory-of-Mind Reasoning in Large Language Models","created":"2024-03-04","cited_by_count":16,"area":"lr"},{"id":"2408.04652","title":"Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference","created":"2024-08-04","cited_by_count":14,"area":"lr"},{"id":"2407.18328","title":"Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring","created":"2024-07-04","cited_by_count":13,"area":null},{"id":"2502.14044","title":"Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data","created":"2025-02-19","cited_by_count":12,"area":"mllm"},{"id":"2502.17204","title":"Order Matters: Investigate the Position Bias in Multi-constraint Instruction Following","created":"2025-02-24","cited_by_count":12,"area":null},{"id":"2505.12075","title":"Do different prompting methods yield a common task representation in language models?","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2311.08883","title":"Distilling Rule-based Knowledge into Large Language Models","created":"2023-11-15","cited_by_count":9,"area":null},{"id":"2402.10453","title":"Steering Conversational Large Language Models for Long Emotional Support Conversations","created":"2024-02-16","cited_by_count":8,"area":null},{"id":"2405.20192","title":"TAIA: Large Language Models are Out-of-Distribution Data Learners","created":"2024-05-30","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":"2402.12713","title":"Are LLMs Rational Investors? A Study on Detecting and Reducing the Financial Bias in LLMs","created":"2024-02-20","cited_by_count":7,"area":null},{"id":"2506.06950","title":"What Makes a Good Natural Language Prompt?","created":"2025-06-07","cited_by_count":7,"area":null},{"id":"2505.07853","title":"CrashSage: A Large Language Model-Centered Framework for Contextual and Interpretable Traffic Crash Analysis","created":"2025-05-08","cited_by_count":6,"area":null},{"id":"2410.23496","title":"Smaller Large Language Models Can Do Moral Self-Correction","created":"2024-10-30","cited_by_count":5,"area":"safety"},{"id":"2502.14133","title":"Self-Regularization with Sparse Autoencoders for Controllable LLM-based Classification","created":"2025-02-19","cited_by_count":5,"area":"mechinterp"},{"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":"2406.17484","title":"MedCare: Advancing Medical LLMs through Decoupling Clinical Alignment and Knowledge Aggregation","created":"2024-06-25","cited_by_count":4,"area":null},{"id":"2409.19680","title":"Instruction Embedding: Latent Representations of Instructions Towards Task Identification","created":"2024-09-29","cited_by_count":4,"area":null},{"id":"2505.08080","title":"Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders","created":"2025-05-12","cited_by_count":4,"area":"mechinterp"},{"id":"2505.23838","title":"Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2507.18203","title":"Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation","created":"2025-07-24","cited_by_count":4,"area":"safety"},{"id":"2508.00459","title":"Thinking Machines: Mathematical Reasoning in the Age of LLMs","created":"2025-08-01","cited_by_count":4,"area":"lr"},{"id":"2510.09359","title":"Understanding the Effects of Domain Finetuning on LLMs","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2510.24331","title":"What do vision-language models see in the context? Investigating multimodal in-context learning","created":"2025-10-28","cited_by_count":4,"area":"mllm"},{"id":"2603.04426","title":"Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2411.11932","title":"Unveiling and Addressing Pseudo Forgetting in Large Language Models","created":"2024-11-18","cited_by_count":3,"area":null},{"id":"2410.01512","title":"InstaTrans: An Instruction-Aware Translation Framework for Non-English Instruction Datasets","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2506.12365","title":"Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics","created":"2025-06-14","cited_by_count":2,"area":"lr"},{"id":"2604.11838","title":"A Layer-wise Analysis of Supervised Fine-Tuning","created":"2026-04-12","cited_by_count":2,"area":null},{"id":"2604.13694","title":"Weight Patching: Toward Source-Level Mechanistic Localization in LLMs","created":"2026-04-15","cited_by_count":2,"area":"mechinterp"},{"id":"2509.02075","title":"How Instruction-Tuning Imparts Length Control: A Cross-Lingual Mechanistic Analysis","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2509.20376","title":"ConceptViz: A Visual Analytics Approach for Exploring Concepts in Large Language Models","created":"2025-09-20","cited_by_count":1,"area":"mechinterp"},{"id":"2510.23636","title":"LLM4Delay: Flight Delay Prediction via Cross-Modality Adaptation of Large Language Models and Aircraft Trajectory Representation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.02060","title":"FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.17623","title":"Unmasking the Factual-Conceptual Gap in Persian Language Models","created":"2026-02-19","cited_by_count":1,"area":null},{"id":"2602.20904","title":"Transcoder Adapters for Reasoning-Model Diffing","created":"2026-02-24","cited_by_count":1,"area":"lr"},{"id":"2604.27637","title":"Optimization before Evaluation: Evaluation with Unoptimised Prompts Can be Misleading","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.12290","title":"Targeted Neuron Modulation via Contrastive Pair Search","created":"2026-05-12","cited_by_count":1,"area":"safety"},{"id":"2605.18025","title":"TeleCom-Bench: How Far Are Large Language Models from Industrial Telecommunication Applications?","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2410.19195","title":"Label Set Optimization via Activation Distribution Kurtosis for Zero-shot Classification with Generative Models","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2506.15480","title":"Instruction Tuning with and without Context: Behavioral Shifts and Downstream Impact","created":"2025-06-18","cited_by_count":0,"area":null},{"id":"2604.06015","title":"How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2608.11138","title":"Attention-Path Fragility as an Uncertainty Signal in Large Language Models","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.14681","title":"Automatic or Controlled? Repetition Priming Reveals Divergent Processing in Base LLMs, Instruct LLMs, and Humans","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.23338","title":"The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.22146","title":"GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.25602","title":"Rewired or Gated? How Instruction Tuning Shapes Knowledge-Conflict Circuits in LLMs","created":"2026-09-22","cited_by_count":0,"area":"mechinterp"},{"id":"2609.38205","title":"The System Prompt Illusion: How Instruction Preambles Modify Computation in Language Models","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}