arXiv:2511. 16992v3 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with human values often involves balancing multiple, conflicting objectives such as helpfulness and harmlessness.
arXiv:2606. 15625v1 Announce Type: new Abstract: The continuous scaling of large language models (LLMs) incurs prohibitive computational costs, making Mixture-of-Experts (MoE) a scalable alternative for efficient fine-tuning via sparse activation.
arXiv:2510. 01167v2 Announce Type: replace-cross Abstract: Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective.
arXiv:2505. 10892v2 Announce Type: replace Abstract: Post-training LLMs with RLHF and preference optimization methods (e.
arXiv:2606. 05613v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) has established cross-lingual versatility as a defining feature of modern systems.
arXiv:2608. 12108v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training across distributed clients while keeping data local.
arXiv:2502. 10239v3 Announce Type: replace-cross Abstract: Federated Learning (FL) is a promising paradigm for finetuning Large Language Models (LLMs) across distributed data sources while preserving data privacy.
arXiv:2604.13175v2 Announce Type: replace-cross Abstract: Large language models can be aligned with human preferences through offline reinforcement learning (RL) on small labeled datasets. While sing...
arXiv:2405. 16472v2 Announce Type: replace Abstract: Contemporary AI faces the challenge of balancing generality with user-specific personalization.
FlexP-SFT introduces an aggregation-free framework for personalized split federated fine-tuning of large language models, eliminating the client-side aggregation step that traditionally causes communication bottlenecks and straggler issues. The method employs a layer‑flexible alignment strategy to balance personalization and generalization without global synchronization, and formulates split‑ratio selection as a resource‑aware discrete optimization problem. Experiments demonstrate that FlexP-SFT improves both accuracy and latency compared to baselines, achieving a superior resource‑accuracy trade‑off.
arXiv:2606. 31524v1 Announce Type: cross Abstract: The Self-Improving Alignment (SAIL) algorithm addresses distribution shift by reducing a bilevel formulation of the problem to an efficient, single-level method.
arXiv:2609.08211v1 Announce Type: new Abstract: Real-world Multi-Objective Reinforcement Learning (MORL) often suffers from sparse rewards, reward conflicts, and late-stage reward tug-of-war, causing...
The paper introduces a latent information sharing scheme for federated learning that mitigates client drift by sharing a small amount of hidden‑layer activations. The authors demonstrate both theoretically and empirically that this approach improves training efficiency while maintaining convergence guarantees and data privacy. Compared to existing methods such as FedProx, SCAFFOLD, FedPVR, FedProto, and SplitFed, the proposed method achieves higher model accuracy within a fixed round budget without adding significant communication overhead.