The field of Retrieval-Augmented Generation (RAG) and human-AI collaboration is rapidly advancing, with a focus on improving the accuracy and efficiency of language models. Recent developments have led to the creation of novel frameworks and methods that enhance the performance of RAG systems, such as the use of retrieval-augmented learning, multi-granularity multimodal retrieval, and adaptive invocation. These advancements have significant implications for various applications, including question answering, document understanding, and human-AI collaboration. Noteworthy papers in this area include 'Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation', which proposes a reward-free self-supervised learning framework for LLMs, and 'SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration', which introduces a novel framework that establishes a bidirectional learning relationship between humans and machines.
Advancements in Retrieval-Augmented Generation and Human-AI Collaboration
Sources
Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation
A Multi-Granularity Multimodal Retrieval Framework for Multimodal Document Tasks
Automated Parsing of Engineering Drawings for Structured Information Extraction Using a Fine-tuned Document Understanding Transformer
Interaction Configurations and Prompt Guidance in Conversational AI for Question Answering in Human-AI Teams
Adversarial Cooperative Rationalization: The Risk of Spurious Correlations in Even Clean Datasets
Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answering
Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing
SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration
Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models
DocSpiral: A Platform for Integrated Assistive Document Annotation through Human-in-the-Spiral
An Analysis of Hyper-Parameter Optimization Methods for Retrieval Augmented Generation
BCause: Human-AI collaboration to improve hybrid mapping and ideation in argumentation-grounded deliberation
LLM-Independent Adaptive RAG: Let the Question Speak for Itself
Adaptive Markup Language Generation for Contextually-Grounded Visual Document Understanding