Cs-Cl
Fine-Tuning Language Models to Know What They Know
Social Catalysts, Not Moral Agents: The Illusion of Alignment in LLM Societies
Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data
AmharicStoryQA: A Multicultural Story Question Answering Benchmark in Amharic
From Task Solving to Robust Real-World Adaptation in LLM Agents
Uncertainty and Fairness Awareness in LLM-Based Recommendation Systems
Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery
InfMem: Learning System-2 Memory Control for Long-Context Agent
Scaling Small Agents Through Strategy Auctions
WideSeek: Advancing Wide Research via Multi-Agent Scaling
Monotonicity as an Architectural Bias for Robust Language Models
Time-Critical Multimodal Medical Transportation: Organs, Patients, and Medical Supplies
Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease Management
Predicting first-episode homelessness among US Veterans using longitudinal EHR data: time-varying models and social risk factors
BinaryPPO: Efficient Policy Optimization for Binary Classification
Evidence from fMRI Supports a Two-Phase Abstraction Process in Language Models
RACA: Representation-Aware Coverage Criteria for LLM Safety Testing
OpenSeal: Good, Fast, and Cheap Construction of an Open-Source Southeast Asian LLM via Parallel Data
Statistical Learning Theory in Lean 4: Empirical Processes from Scratch
Using Correspondence Patterns to Identify Irregular Words in Cognate sets Through Leave-One-Out Validation
Language Steering for Multilingual In-Context Learning
