We look at the limitations of AI-generated text detection technology presented at ACL 2024 and the latest research that addresses them.
This piece summarizes the trends and key methodologies of the latest AI-generated text detection technologies presented at ACL 2024.
This piece examines the methodologies for evaluating LLM faithfulness and the latest research trends for improving efficiency, as discussed at ACL 2024.
This piece examines the LLM reliability evaluation methodologies and research trends in complex task performance and efficiency presented at ACL 2024.
Through an ACL 2024 workshop, LG AI Research introduced the importance of developing LLMs that reflect cultural values and biases, along with related research.
This article looks at the latest research trends on how LLMs can reflect and measure diverse cultural values and social biases.
LG AI Research proposed Projection Regret, a technique that leverages Diffusion models to reduce interference from background information and improve novelty detection performance.
LG AI Research proposed Projection Regret, a technique that uses a Diffusion model to reduce background noise and improve anomaly detection performance.
LG AI Research has introduced an AI Red Team that checks vulnerabilities from an offensive perspective to enhance the security and reliability of generative AI.
It introduces the concept of AI Red Team and its step-by-step attack strategies for detecting and defending against vulnerabilities in generative AI.
LG AI Research conducts research to define and systematically classify the practical risks that AI can cause through its AI Ethics Seminar.
This article analyzes Microsoft's and Google's AI toolkits to design trustworthy AI experiences and presents practical application methods.
To design trustworthy AI experiences, this analyzes Microsoft's and Google's AI Toolkits and presents practical application guidelines.
Explores the potential for autonomous collaboration among AI agents and the changes they could bring to social structures.
It analyzes the autonomous decision-making and cooperation patterns of AI Agents through simulations and presents the need for ethical mechanisms.
LG AI Research has released 3 EXAONE 3.5 open-source models that maximize performance and efficiency.
LG AI Research has released 3 EXAONE 3.5 models as open source, capturing both performance and cost-efficiency.
LG AI Research is researching AI-based auto-routing technology to streamline complex PCB design processes.
LG AI Research developed a PCB automatic routing technology that combines Grid-based and Continuous Space methods to solve complex constraint conditions.
It analyzes deceptive patterns that can occur during the UI/UX design process of AI services and proposes ethical design approaches.
LG AI Research proposed a new benchmark that goes beyond the limitations of existing Gaussian-data-centric approaches to verify mutual information (MI) estimation performance on unstructured data.
LG AI Research proposed a new benchmark that can rigorously verify mutual information (MI) estimation performance in unstructured data settings.
LG AI Research has proposed a new technique that uses B-spline to dynamically normalize tabular data according to its complex distributions.
LG AI Research proposed a Tabular data normalization technique using B-splines that dynamically transforms according to data characteristics.
AI Briefing