7 citations · 40 across the 58 of their papers we have counts for
16 papers · 1 filter
EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion
Pengfei Cao, Zeao Ji, Daojian Zeng +2
Adjusting the outdated knowledge of large language models (LLMs) after deployment remains a major challenge. This difficulty has spurred the development of knowledge editing, which…
Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning
Sirui Liang, Pengfei Cao, Jian Zhao +3
Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further im…
Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
Zhuoran Jin, Hongbang Yuan, Kejian Zhu +5
Reward models (RMs) play a critical role in aligning AI behaviors with human preferences, yet they face two fundamental challenges: (1) Modality Imbalance, where most RMs are mainl…
Towards Atoms of Large Language Models
Chenhui Hu, Pengfei Cao, Yubo Chen +2
The fundamental representational units (FRUs) of large language models (LLMs) remain undefined, limiting further understanding of their underlying mechanisms. In this paper, we int…
LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
Xixun Lin, Yucheng Ning, Jingwen Zhang +21
Driven by the rapid advancements of Large Language Models (LLMs), LLM-based agents have emerged as powerful intelligent systems capable of human-like cognition, reasoning, and inte…
Task-Stratified Knowledge Scaling Laws for Post-Training Quantized Large Language Models
Chenxi Zhou, Pengfei Cao, Jiang Li +4
Post-Training Quantization (PTQ) is a critical strategy for efficient Large Language Models (LLMs) deployment. However, existing scaling laws primarily focus on general performance…
Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
Tianyi Men, Zhuoran Jin, Pengfei Cao +3
As Multimodal Large Language Models (MLLMs) advance, multimodal agents show promise in real-world tasks like web navigation and embodied intelligence. However, due to limitations i…
Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models
Jiaxiang Liu, Boxuan Xing, Chenhao Yuan +8
As large language models (LLMs) continue to advance, there is a growing urgency to enhance the interpretability of their internal knowledge mechanisms. Consequently, many interpret…
MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos
Kejian Zhu, Zhuoran Jin, Hongbang Yuan +6
The sequential structure of videos poses a challenge to the ability of multimodal large language models (MLLMs) to locate multi-frame evidence and conduct multimodal reasoning. How…
Large Language Models for Planning: A Comprehensive and Systematic Survey
Pengfei Cao, Tianyi Men, Wencan Liu +7
Planning represents a fundamental capability of intelligent agents, requiring comprehensive environmental understanding, rigorous logical reasoning, and effective sequential decisi…
Tianyi: A Traditional Chinese Medicine all-rounder language model and its Real-World Clinical Practice
Zhi Liu, Tao Yang, Jing Wang +10
Natural medicines, particularly Traditional Chinese Medicine (TCM), are gaining global recognition for their therapeutic potential in addressing human symptoms and diseases. TCM, w…
Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing
Jiakuan Xie, Pengfei Cao, Yubo Chen +2
Knowledge editing, which aims to update the knowledge encoded in language models, can be deceptive. Despite the fact that many existing knowledge editing algorithms achieve near-pe…
Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
Yupu Hao, Pengfei Cao, Zhuoran Jin +4
Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools. However, most of the current…
Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
Jiachun Li, Pengfei Cao, Zhuoran Jin +6
Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on trainin…
The Knowledge Microscope: Features as Better Analytical Lenses than Neurons
Yuheng Chen, Pengfei Cao, Kang Liu +1
Previous studies primarily utilize MLP neurons as units of analysis for understanding the mechanisms of factual knowledge in Language Models (LMs); however, neurons suffer from pol…
Short-time Variational Mode Decomposition
Hao Jia, Pengfei Cao, Tong Liang +7
Variational mode decomposition (VMD) and its extensions like Multivariate VMD (MVMD) decompose signals into ensembles of band-limited modes with narrow central frequencies. These m…