8 papers
Layer-Order Inversion: Rethinking Latent Multi-Hop Reasoning in Large Language Models
Xukai Liu, Ye Liu, Jipeng Zhang +3
Large language models (LLMs) perform well on multi-hop reasoning, yet how they internally compose multiple facts remains unclear. Recent work proposes \emph{hop-aligned circuit hyp…
Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
Haoyu Tang, Ye Liu, Xi Zhao +5
Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking s…
Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering
Jiajun Zhu, Ye Liu, Meikai Bao +3
Recently, large language models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, yet they remain prone to hallucinations when reasoning with i…
MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modality
Shuaike Li, Kai Zhang, Qi Liu +1
Knowledge editing is a technique for efficiently and accurately updating the knowledge of large language models (LLMs) to alleviate obsolescence and correct errors. However, most e…
Unveiling the Magic of Code Reasoning through Hypothesis Decomposition and Amendment
Yuze Zhao, Tianyun Ji, Wenjun Feng +6
The reasoning abilities are one of the most enigmatic and captivating aspects of large language models (LLMs). Numerous studies are dedicated to exploring and expanding the boundar…
SentiFormer: Metadata Enhanced Transformer for Image Sentiment Analysis
Bin Feng, Shulan Ruan, Mingzheng Yang +4
As more and more internet users post images online to express their daily emotions, image sentiment analysis has attracted increasing attention. Recently, researchers generally ten…