Search Results for author: Xuansheng Wu

Found 16 papers, 8 papers with code

A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models

no code implementations7 Mar 2025 Dong Shu, Xuansheng Wu, Haiyan Zhao, Daking Rai, Ziyu Yao, Ninghao Liu, Mengnan Du

Despite the challenges that remain around SAE implementation and scaling, they continue to provide valuable tools for understanding the internal mechanisms of large language models.

Interpreting and Steering LLMs with Mutual Information-based Explanations on Sparse Autoencoders

no code implementations21 Feb 2025 Xuansheng Wu, Jiayi Yuan, Wenlin Yao, Xiaoming Zhai, Ninghao Liu

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses.

Self-Regularization with Latent Space Explanations for Controllable LLM-based Classification

no code implementations19 Feb 2025 Xuansheng Wu, Wenhao Yu, Xiaoming Zhai, Ninghao Liu

In training the classification model, we propose a simple and effective regularizer, by minimizing the similarity between the classifier weights and the identified unintended feature, to remove the impacts of these unintended features toward classification.

Fairness text-classification +1

LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models

no code implementations2 Oct 2024 Zhenyue Qin, Yu Yin, Dylan Campbell, Xuansheng Wu, Ke Zou, Yih-Chung Tham, Ninghao Liu, Xiuzhen Zhang, Qingyu Chen

The prevalence of vision-threatening eye diseases is a significant global burden, with many cases remaining undiagnosed or diagnosed too late for effective treatment.

Hallucination

Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring

no code implementations4 Jul 2024 Xuansheng Wu, Padmaja Pravin Saraf, Gyeonggeon Lee, Ehsan Latif, Ninghao Liu, Xiaoming Zhai

Specifically, we prompt LLMs to generate analytic rubrics that they use to assign scores and study the alignment gap with human grading rubrics.

Logical Reasoning

Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era

1 code implementation13 Mar 2024 Xuansheng Wu, Haiyan Zhao, Yaochen Zhu, Yucheng Shi, Fan Yang, Tianming Liu, Xiaoming Zhai, Wenlin Yao, Jundong Li, Mengnan Du, Ninghao Liu

Therefore, in this paper, we introduce Usable XAI in the context of LLMs by analyzing (1) how XAI can benefit LLMs and AI systems, and (2) how LLMs can contribute to the advancement of XAI.

InFoBench: Evaluating Instruction Following Ability in Large Language Models

1 code implementation7 Jan 2024 Yiwei Qin, Kaiqiang Song, Yebowen Hu, Wenlin Yao, Sangwoo Cho, Xiaoyang Wang, Xuansheng Wu, Fei Liu, PengFei Liu, Dong Yu

This paper introduces the Decomposed Requirements Following Ratio (DRFR), a new metric for evaluating Large Language Models' (LLMs) ability to follow instructions.

Instruction Following

Applying Large Language Models and Chain-of-Thought for Automatic Scoring

no code implementations30 Nov 2023 Gyeong-Geon Lee, Ehsan Latif, Xuansheng Wu, Ninghao Liu, Xiaoming Zhai

We found a more balanced accuracy across different proficiency categories when CoT was used with a scoring rubric, highlighting the importance of domain-specific reasoning in enhancing the effectiveness of LLMs in scoring tasks.

Few-Shot Learning Prompt Engineering +1

Could Small Language Models Serve as Recommenders? Towards Data-centric Cold-start Recommendations

1 code implementation29 Jun 2023 Xuansheng Wu, Huachi Zhou, Yucheng Shi, Wenlin Yao, Xiao Huang, Ninghao Liu

To evaluate our approach, we introduce a cold-start recommendation benchmark, and the results demonstrate that the enhanced small language models can achieve comparable cold-start recommendation performance to that of large models with only $17\%$ of the inference time.

In-Context Learning Language Modeling +3

AGI: Artificial General Intelligence for Education

no code implementations24 Apr 2023 Ehsan Latif, Gengchen Mai, Matthew Nyaaba, Xuansheng Wu, Ninghao Liu, Guoyu Lu, Sheng Li, Tianming Liu, Xiaoming Zhai

AGI, driven by the recent large pre-trained models, represents a significant leap in the capability of machines to perform tasks that require human-level intelligence, such as reasoning, problem-solving, decision-making, and even understanding human emotions and social interactions.

Decision Making Fairness

Black-box Backdoor Defense via Zero-shot Image Purification

1 code implementation NeurIPS 2023 Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Jin Sun, Ninghao Liu

Defending against such attacks is challenging, especially for real-world black-box models where only query access is permitted.

backdoor defense

A Survey of Graph Prompting Methods: Techniques, Applications, and Challenges

no code implementations13 Mar 2023 Xuansheng Wu, Kaixiong Zhou, Mingchen Sun, Xin Wang, Ninghao Liu

In particular, we introduce the basic concepts of graph prompt learning, organize the existing work of designing graph prompting functions, and describe their applications and future challenges.

Prompt Learning Survey

NoPPA: Non-Parametric Pairwise Attention Random Walk Model for Sentence Representation

1 code implementation24 Feb 2023 Xuansheng Wu, Zhiyi Zhao, Ninghao Liu

We propose a novel non-parametric/un-trainable language model, named Non-Parametric Pairwise Attention Random Walk Model (NoPPA), to generate sentence embedding only with pre-trained word embedding and pre-counted word frequency.

Language Modeling Language Modelling +3

Cannot find the paper you are looking for? You can Submit a new open access paper.