paper-with-me

Papers

Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective

2026-05-03 · Hengyu Liu, Tianyi Li, Zhihong Cui, Yushuai Li, Zhangkai Wu, Torben Bach Pedersen, Kristian Torp, Christian S. Jensen arxiv

This position paper argues that reliable AI requires infrastructure for human validation of implicit knowledge. AI learns from both explicit knowledge (papers, documentation, structured databases) and implicit knowledge (reasoning patterns, debugging processes, intermediate steps). Implicit knowledge remains unexternalized because documentation cost exceeds perceived value -- yet AI learns from it indiscriminately, acquiring both beneficial patterns and harmful biases. Current reliability methods can only verify explicit knowledge against sources, creating a fundamental gap: the most valuable AI capabilities (reasoning, judgment, intuition) are precisely those we cannot verify. We propose Knowledge Objects (KOs) -- structured artifacts that externalize implicit knowledge into forms humans can inspect, verify, and endorse. KOs transform verification economics: what was previously too costly to verify becomes feasible, enabling accumulated human validation to improve reliability over time.

📄 PDF Abstract BibTeX arXiv:2605.02010

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation

2021-10-16 · ACL 2022 5 · Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim 외

Implicit knowledge, such as common sense, is key to fluid human conversations. Current neural response generation (RG) models are trained to generate responses directly, omitting unstated implicit knowledge. In this pape…

Common Sense ReasoningExplainable ModelsResponse Generation

Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria

2026-05-08 · Juanxi Tian, Fengyuan Liu, Jiaming Han, Yilei Jiang 외 arxiv

Aligning multimodal generative models with human preferences demands reward signals that respect the compositional, multi-dimensional structure of human judgment. Prevailing RLHF approaches reduce this structure to scala…

Text-to-Image GenerationImage Editing

Data Therapist: Eliciting Domain Knowledge from Subject Matter Experts Using Large Language Models

2025-05-01 · Sungbok Shin, Hyeon Jeon, Sanghyun Hong, Niklas Elmqvist

Effective data visualization requires not only technical proficiency but also a deep understanding of the domain-specific context in which data exists. This context often includes tacit knowledge about data provenance, q…

Data VisualizationLanguage ModelingLanguage ModellingLarge Language Model

Large Language Models and the Rationalist Empiricist Debate

2024-10-16 · David King

To many Chomsky's debates with Quine and Skinner are an updated version of the Rationalist Empiricist debates of the 17th century. The consensus being that Chomsky's Rationalism was victorious. This dispute has reemerged…

Toward Effective and Reliable LLM Agents via Dynamic Ontology

2026-08-24 · Xiaohui Zhang, Zequn Sun, Chengyuan Yang, Yuanning Cui 외 arxiv

Large language model (LLM) agents rely heavily on knowledge encoded in model parameters or presented as unstructured context. In domain-specific tasks, this leaves important semantic connections implicit. This often resu…

Decision Making