research-papers

research-papers

Automatic Root Cause Analysis via Large Language Models for Cloud Incidents

Original Paper: https://arxiv.org/abs/2305.15778 By: Yinfang Chen, Huaibing Xie, Minghua Ma, Yu Kang, Xin Gao, Liu Shi, Yunjie Cao, Xuedong Gao, Hao Fan, Ming Wen, Jun Zeng, Supriyo Ghosh, Xuchao Zhang, Chaoyun Zhang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Tianyin Xu Abstract: Ensuring the reliability and

research-papers

Promise: Prompt-driven 3D Medical Image Segmentation Using Pretrained Image Foundation Models

Original Paper: https://arxiv.org/abs/2310.19721 By: Hao Li, Han Liu, Dewei Hu, Jiacheng Wang, Ipek Oguz Abstract: To address prevalent issues in medical imaging, such as data acquisition challenges and label availability, transfer learning from natural to medical image domains serves as a viable strategy to produce

research-papers

A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Models

Original Paper: https://arxiv.org/abs/2311.07491 By: Hejing Cao, Zhenwei An, Jiazhan Feng, Kun Xu, Liwei Chen, Dongyan Zhao Abstract: While large language models exhibit remarkable performance in the Question Answering task, they are susceptible to hallucinations. Challenges arise when these models grapple with understanding multi-hop relations in

research-papers

Semi-Structured Chain-of-Thought: Integrating Multiple Sources of Knowledge for Improved Language Model Reasoning

Original Paper: https://arxiv.org/abs/2311.08505 By: Xin Su, Tiep Le, Steven Bethard, Phillip Howard Abstract: An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge,

research-papers

Testing LLMs on Code Generation with Varying Levels of Prompt Specificity

Original Paper: https://arxiv.org/abs/2311.07599 By: Lincoln Murr, Morgan Grainger, David Gao Abstract: Large language models (LLMs) have demonstrated unparalleled prowess in mimicking human-like text generation and processing. Among the myriad of applications that benefit from LLMs, automated code generation is increasingly promising. The potential to transform

research-papers

Large Language Models and Prompt Engineering for Biomedical Query Focused Multi-Document Summarisation

Original Paper: https://arxiv.org/abs/2312.04344 By: Diego Mollá Abstract: This paper reports on the use of prompt engineering and GPT-3.5 for biomedical query-focused multi-document summarisation. Using GPT-3.5 and appropriate prompts, our system achieves top ROUGE-F1 results in the task of obtaining short-paragraph-sized answers to biomedical

research-papers

A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Original Paper: https://arxiv.org/abs/2311.05232 By: Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qianglong Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, Ting Liu Abstract: The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), leading

research-papers

Chain-of-Thought Reasoning is a Policy Improvement Operator

Original Paper: https://arxiv.org/abs/2309.08589 By: Hugh Zhang, David C. Parkes Abstract: Large language models have astounded the world with fascinating new capabilities. However, they currently lack the ability to teach themselves new skills, relying instead on large amounts of human-generated training data. We introduce SECToR (Self-Education

research-papers

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training

Original Paper: https://arxiv.org/abs/2311.04155 By: Jiale Cheng, Xiao Liu, Kehan Zheng, Pei Ke, Hongning Wang, Yuxiao Dong, Jie Tang, Minlie Huang Abstract: Large language models (LLMs) have shown impressive success in various applications. However, these models are often not well aligned with human intents, which calls

research-papers

AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors

Original Paper: https://arxiv.org/abs/2310.17419 By: You-Ming Chang, Chen Yeh, Wei-Chen Chiu, Ning Yu Abstract: Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real and fake

research-papers

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

Original Paper: https://arxiv.org/abs/2311.01011 By: Sam Toyer, Olivia Watkins, Ethan Adrian Mendes, Justin Svegliato, Luke Bailey, Tiffany Wang, Isaac Ong, Karim Elmaaroufi, Pieter Abbeel, Trevor Darrell, Alan Ritter, Stuart Russell Abstract: While Large Language Models (LLMs) are increasingly being used in real-world applications, they remain vulnerable

research-papers

Robust Safety Classifier for Large Language Models: Adversarial Prompt Shield

Original Paper: https://arxiv.org/abs/2311.00172 By: Jinhwa Kim, Ali Derakhshan, Ian G. Harris Abstract: Large Language Models' safety remains a critical concern due to their vulnerability to adversarial attacks, which can prompt these systems to produce harmful responses. In the heart of these systems lies a