collaborators

9 papers

cs.CL2026

Dual Attention Residuals

Xingda Yu, Yining Li, Xinzhang Liu +5

Recent work extends Transformer residual pathways along two complementary axes: historical retrieval selects information from earlier depths, whereas multi-stream methods maintain…

cs.CL2026

Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization

Mingkuan Zhao, Wentao Hu, Tianchen Huang +6

Hallucination in Large Language Models (LLMs), characterized by the generation of content inconsistent with contextual facts or logical constraints -- remains a persistent challeng…

cs.CL2026

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models

Shuo Nie, Hexuan Deng, Chao Wang +6

As large language models become smaller and more efficient, small reasoning models (SRMs) are crucial for enabling chain-of-thought (CoT) reasoning in resource-constrained settings…

cs.LG2026

Awakening Dormant Experts:Counterfactual Routing to Mitigate MoE Hallucinations

Wentao Hu, Yanbo Zhai, Xiaohui Hu +6

Sparse Mixture-of-Experts (MoE) models have achieved remarkable scalability, yet they remain vulnerable to hallucinations, particularly when processing long-tail knowledge. We iden…

cs.LG2026

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation

Junlin Li, Shuangyong Song, Guodong Du +6

Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhe…

cs.CL2026

UniARM: Towards a Unified Autoregressive Reward Model for Multi-Objective Test-Time Alignment

Hongyan Xie, Yikun Ban, Ruiyu Fang +6

Multi-objective alignment aims to align LLM responses with multiple human preference objectives. Among existing methods, guiding the generation of frozen LLMs through autoregressiv…