research-papers

OpenAgents: An Open Platform for Language Agents in the Wild

Original Paper: https://arxiv.org/abs/2310.10634 By: Tianbao Xie, Fan Zhou, Zhoujun Cheng, Peng Shi, Luoxuan Weng, Yitao Liu, Toh Jing Hua, Junning Zhao, Qian Liu, Che Liu, Leo Z. Liu, Yiheng Xu, Hongjin Su, Dongchan Shin, Caiming Xiong, Tao Yu Abstract: Language agents show potential in being

Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks

Original Paper: https://arxiv.org/abs/2310.10077 By: Shuyu Jiang, Xingshu Chen, Rui Tang Abstract: Recently, Large language models (LLMs) with powerful general capabilities have been increasingly integrated into various Web applications, while undergoing alignment training to ensure that the generated content aligns with user intent and ethics. Unfortunately,

Autonomous Tree-search Ability of Large Language Models

Original Paper: https://arxiv.org/abs/2310.10686 By: Zheyu Zhang, Zhuorui Ye, Yikang Shen, Chuang Gan Abstract: Large Language Models have excelled in remarkable reasoning capabilities with advanced prompting techniques, but they fall short on tasks that require exploration, strategic foresight, and sequential decision-making. Recent works propose to utilize

PromptTTS 2: Describing and Generating Voices with Text Prompt

Original Paper: https://arxiv.org/abs/2309.02285 By: Yichong Leng, Zhifang Guo, Kai Shen, Xu Tan, Zeqian Ju, Yanqing Liu, Yufei Liu, Dongchao Yang, Leying Zhang, Kaitao Song, Lei He, Xiang-Yang Li, Sheng Zhao, Tao Qin, Jiang Bian Abstract: Speech conveys more information than text, as the same word

Re-Reading Improves Reasoning in Large Language Models

Original Paper: https://arxiv.org/abs/2309.06275 By: Xiaohan Xu, Chongyang Tao, Tao Shen, Can Xu, Hongbo Xu, Guodong Long, Jian-guang Lou Abstract: To enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs), we introduce a simple, yet general and effective prompting method, Re2, i.e., \textbf{Re}

Prompt Engineering or Fine Tuning: An Empirical Assessment of Large Language Models in Automated Software Engineering Tasks

Original Paper: https://arxiv.org/abs/2310.10508 By: Jiho Shin, Clark Tang, Tahmineh Mohati, Maleknaz Nayebi, Song Wang, Hadi Hemmati Abstract: In this paper, we investigate the effectiveness of state-of-the-art LLM, i.e., GPT-4, with three different prompting engineering techniques (i.e., basic prompting, in-context learning, and task-specific prompting)

Mistral 7B

Original Paper: https://arxiv.org/abs/2310.06825 By: Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William

research-papers

Guiding Large Language Models via Directional Stimulus Prompting

Original Paper: https://arxiv.org/abs/2302.11520 By: Zekun Li, Baolin Peng, Pengcheng He, Michel Galley, Jianfeng Gao, Xifeng Yan Abstract: We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a

Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond

Original Paper: https://arxiv.org/abs/2310.06147 By: Hao Sun Abstract: Recent advancements in Large Language Models (LLMs) have garnered wide attention and led to successful products such as ChatGPT and GPT-4. Their proficiency in adhering to instructions and delivering harmless, helpful, and honest (3H) responses can largely be

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Original Paper: https://arxiv.org/abs/2310.05736 By: Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, Lili Qiu Abstract: Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts

Text-driven Prompt Generation for Vision-Language Models in Federated Learning

Original Paper: https://arxiv.org/abs/2310.06123 By: Chen Qiu, Xingyu Li, Chaithanya Kumar Mummadi, Madan Ravi Ganesh, Zhenzhen Li, Lu Peng, Wan-Yi Lin Abstract: Prompt learning for vision-language models, e.g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution

Walking Down the Memory Maze: Beyond Context Limit through Interactive Reading

Original Paper: https://arxiv.org/abs/2310.05029 By: Howard Chen, Ramakanth Pasunuru, Jason Weston, Asli Celikyilmaz Abstract: Large language models (LLMs) have advanced in large strides due to the effectiveness of the self-attention mechanism that processes and compares all tokens at once. However, this mechanism comes with a fundamental