A survey of large language models
Language is essentially a complex, intricate system of human expressions governed by
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …
grammatical rules. It poses a significant challenge to develop capable AI algorithms for …
Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration
Human intelligence thrives on the concept of cognitive synergy, where collaboration and
information integration among different cognitive processes yield superior outcomes …
information integration among different cognitive processes yield superior outcomes …
Self-verification improves few-shot clinical information extraction
Extracting patient information from unstructured text is a critical task in health decision-
support and clinical research. Large language models (LLMs) have shown the potential to …
support and clinical research. Large language models (LLMs) have shown the potential to …
Enable language models to implicitly learn self-improvement from data
Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended
text generation tasks. However, the inherent open-ended nature of these tasks implies that …
text generation tasks. However, the inherent open-ended nature of these tasks implies that …
Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
Recent progress in LLMs discussion suggests that multi-agent discussion improves the
reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic …
reasoning abilities of LLMs. In this work, we reevaluate this claim through systematic …
Literature Review of AI Hallucination Research Since the Advent of ChatGPT: Focusing on Papers from arXiv
DM Park, HJ Lee - Informatization Policy, 2024 - koreascience.kr
Hallucination is a significant barrier to the utilization of large-scale language models or
multimodal models. In this study, we collected 654 computer science papers with" …
multimodal models. In this study, we collected 654 computer science papers with" …
Autohall: Automated hallucination dataset generation for large language models
While Large language models (LLMs) have garnered widespread applications across
various domains due to their powerful language understanding and generation capabilities …
various domains due to their powerful language understanding and generation capabilities …
Natural language deduction with incomplete information
A growing body of work studies how to answer a question or verify a claim by generating a
natural language" proof": a chain of deductive inferences yielding the answer based on a set …
natural language" proof": a chain of deductive inferences yielding the answer based on a set …
Parameter-efficient tuning helps language model alignment
Aligning large language models (LLMs) with human preferences is essential for safe and
useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct …
useful LLMs. Previous works mainly adopt reinforcement learning (RLHF) and direct …
Forward-backward reasoning in large language models for mathematical verification
Self-Consistency samples diverse reasoning chains with answers and chooses the final
answer by majority voting. It is based on forward reasoning and cannot further improve …
answer by majority voting. It is based on forward reasoning and cannot further improve …