12 papers
Sycophancy Suppression Can Impair Rational Updating: Anti-Sycophancy Should Preserve the Ability to Update
Huanhuan Ma, Henry Peng Zou, Chengze Li +3
Large language models often exhibit sycophancy, revising their answers to align with users when users push back. Such answer flips, however, can arise from different causes. One po…
Online Test-Time Adaptation for Generalizable Dynamic Graph Anomaly Detection
Jialun Zheng, Hanchen Yang, Jiannong Cao +3
Generalizable dynamic graph anomaly detection (DGAD) enables pretrained detectors to identify anomalies in unseen target domains without costly retraining. However, existing method…
FORTIS: Benchmarking Over-Privilege in Agent Skills
Shawn Li, Chenxiao Yu, Han Wang +8
Large language model agents increasingly operate through an intermediate skill layer that mediates between user intent and concrete task execution. This layer is widely treated as…
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
Langzhou He, Junyou Zhu, Yue Zhou +7
Agentic reinforcement learning trains large language models using multi-turn trajectories that interleave long reasoning traces with short environment-facing actions. Common policy…
Decoupled and Divergence-Conditioned Prompt for Multi-domain Dynamic Graph Foundation Models
Haonan Yuan, Qingyun Sun, Junhua Shi +3
Dynamic graphs are ubiquitous in real-world systems, and building generalizable dynamic Graph Foundation Models has become a frontier in graph learning. However, dynamic graphs fro…
Filter-then-Weight: Online Data Selection and Reweighting for LLM Fine-Tuning
Fangxin Wang, Peyman Baghershahi, Langzhou He +3
Gradient-based data selection offers a principled framework for estimating sample utility in large language model (LLM) fine-tuning, but existing methods are mostly designed for of…
Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuning
Lingzhe Zhang, Tong Jia, Yunpeng Zhai +6
Reinforcement fine-tuning (RFT) has become a core paradigm for post-training large language models, yet its training process remains highly fragile. Existing efforts mainly improve…
Locally Confident, Globally Stuck: The Quality-Exploration Dilemma in Diffusion Language Models
Liancheng Fang, Aiwei Liu, Henry Peng Zou +7
Diffusion large language models (dLLMs) theoretically permit token decoding in arbitrary order, a flexibility that could enable richer exploration of reasoning paths than autoregre…
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
Yujie Feng, Hao Wang, Jian Li +6
Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. Memory replay methods are widely used for…
DP-DGAD: A Generalist Dynamic Graph Anomaly Detector with Dynamic Prototypes
Jialun Zheng, Jie Liu, Jiannong Cao +4
Dynamic graph anomaly detection (DGAD) is essential for identifying anomalies in evolving graphs across domains such as finance, traffic, and social networks. Recently, generalist…
GeoEdit: Geometric Knowledge Editing for Large Language Models
Yujie Feng, Liming Zhan, Zexin Lu +6
Regular updates are essential for maintaining up-to-date knowledge in large language models (LLMs). Consequently, various model editing methods have been developed to update specif…
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning
Yujie Feng, Xujia Wang, Zexin Lu +7
Continual learning (CL) is crucial for deploying large language models (LLMs) in dynamic real-world environments without costly retraining. While recent model ensemble and model me…