CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling
Research
Research News
New papers, breakthroughs and academic AI research
Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment
Research
Symphony for Text Generation: Benchmarking Clinical Note Generation
Research
Disentangling Paradigm, Identifier, and Decoding in Generative Retrieval
Research
DeltaTTT: Layerwise Optimization for Nonlinear Recurrent Memory
Research
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Research
Boosting Large Language Models with Mask Fine-Tuning
Research
A Systematic Study of Semantic ID Spaces for Generative Information Retrieval
Research
Do Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph Learning
Research
FedCoT: Communication-Efficient Federated Reasoning Enhancement for Large Language Models
Research
Learning a Ranking from Human Feedback in Log-Concave Random Utility Models
Research
Even Small Reasoners Should Quote Their Sources: Introducing the Pleias-RAG Model Family
Research