Generative Large Language Model

Generative Large Language Models (LLMs) are powerful AI systems capable of generating human-quality text, enabling advancements in various applications like dialogue systems and machine translation. Current research focuses on improving efficiency (e.g., through quantization and parallel processing), addressing biases and safety concerns (including backdoor attacks), and enhancing performance in low-resource languages via techniques like fine-tuning and prompt engineering. The impact of LLMs is significant, driving progress in natural language processing and impacting diverse fields through improved automation, enhanced accessibility, and more effective information retrieval and analysis.

Papers

May 22, 2023

Teaching Probabilistic Logical Reasoning to Transformers
Aliakbar Nafar, Kristen Brent Venable, Parisa Kordjamshidi
Language Model Transformer Megatron Decepticons Transformer Based Language Model Generative Large Language Model Probabilistic Reasoning

May 16, 2023

SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
Xupeng Miao, Gabriele Oliaro, Zhihao Zhang, Xinhao Cheng, Zeyu Wang, Zhengxin Zhang, Rae Ying Yee Wong, Alan Zhu, Lijie Yang, Xiaoxiang Shi, Chunan Shi, Zhuoming Chen, Daiyaan Arfeen, Reyna Abhyankar, Zhihao Jia
Verification Task Generative Large Language Model Large Language Model Inference Generative LLM

April 25, 2023

Empirical Evaluation of ChatGPT on Requirements Information Retrieval Under Zero-Shot Setting
Jianzhang Zhang, Yiyang Chen, Nan Niu, Yinglin Wang, Chuang Liu
ChatGPT Generated Conversation Generative Large Language Model Empirical Evaluation

March 24, 2023

Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models
Qingyu Lu, Baopu Qiu, Liang Ding, Kanjian Zhang, Tom Kocmi, Dacheng Tao
Machine Translation Translation Quality Generative Large Language Model Machine Translation Evaluation

March 21, 2023

March 15, 2023

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models
Potsawee Manakul, Adian Liusie, Mark J. F. Gales
Fact Checking Generative Large Language Model Hallucination Detection Non Negative Textual Response Factuality Detection

February 28, 2023

Large Language Models Are State-of-the-Art Evaluators of Translation Quality
Tom Kocmi, Christian Federmann
Human Evaluation Translation Quality Generative Large Language Model GPT Based

February 24, 2023

Spanish Built Factual Freectianary (Spanish-BFF): the first AI-generated free dictionary
Miguel Ortega-Martín, Óscar García-Sierra, Alfonso Ardoiz, Juan Carlos Armenteros, Jorge Álvarez, Adrián Alonso
Generative Large Language Model French Dictionary Continuous Spanish Multi FAct Linguistic Resource Spanish Dictionary

February 11, 2023

Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models
Renat Aksitov, Chung-Ching Chang, David Reitter, Siamak Shakeri, Yunhsuan Sung
Large Language Model Language Model Generative Large Language Model Source Attribution Knowledge Grounded Fluency Assessment

Generative Large Language Model

Papers

Teaching Probabilistic Logical Reasoning to Transformers

SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification

Empirical Evaluation of ChatGPT on Requirements Information Retrieval Under Zero-Shot Setting

Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models

Fundamentals of Generative Large Language Models and Perspectives in Cyber-Defense

Large Language Models Can Be Used to Estimate the Latent Positions of Politicians

SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

Large Language Models Are State-of-the-Art Evaluators of Translation Quality

Spanish Built Factual Freectianary (Spanish-BFF): the first AI-generated free dictionary

Characterizing Attribution and Fluency Tradeoffs for Retrieval-Augmented Large Language Models