Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs Paper • 2512.05648 • Published Dec 5, 2025
The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity? Paper • 2601.23045 • Published 18 days ago
Training Dynamics of the Cooldown Stage in Warmup-Stable-Decay Learning Rate Scheduler Paper • 2508.01483 • Published Aug 2, 2025 • 1
Apertus: Democratizing Open and Compliant LLMs for Global Language Environments Paper • 2509.14233 • Published Sep 17, 2025 • 16
The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity? Paper • 2601.23045 • Published 18 days ago
PiCSAR: Probabilistic Confidence Selection And Ranking Paper • 2508.21787 • Published Aug 29, 2025 • 4
BaCaDI: Bayesian Causal Discovery with Unknown Interventions Paper • 2206.01665 • Published Jun 3, 2022 • 2
Self-Training Large Language Models for Tool-Use Without Demonstrations Paper • 2502.05867 • Published Feb 9, 2025
Parameter-Efficient Fine-Tuning of LLaMA for the Clinical Domain Paper • 2307.03042 • Published Jul 6, 2023
Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them Paper • 2507.10616 • Published Jul 13, 2025 • 1
An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering Paper • 2503.23415 • Published Mar 30, 2025 • 1
Lost in Time: Clock and Calendar Understanding Challenges in Multimodal LLMs Paper • 2502.05092 • Published Feb 7, 2025 • 8
The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training Paper • 2501.18965 • Published Jan 31, 2025 • 7
CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning Paper • 2410.10336 • Published Oct 14, 2024 • 2
Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering Paper • 2410.15999 • Published Oct 21, 2024 • 20