Teaching AI to Ask Better Questions: Meet Nous

Kari Jaaskelainen

04 Nov 2025 — 1 min read

TL;DR

We often know what we want, but struggle to tell AI. This “intention gap” wastes time. This paper reframes AI from a passive follower to a Socratic partner that asks the right questions.

What’s new? An agent called Nous learns an inquiry policy that maximizes information gained from each question—grounded in Shannon entropy.
No costly labels: Information gain becomes the reward, removing the need for human preference annotations.
Does it work? In scientific diagram generation, Nous reached higher quality with fewer back-and-forths, across novice to expert users, and showed signs of generalizing beyond diagrams.

Think of it as GPS for intent: every question shrinks uncertainty until the destination is clear.

Paper: http://arxiv.org/abs/2510.27410v1 • Authors: Jianwen Sun, Yukang Feng, Yifan Chang, Chuanhao Li, Zizhen Li, Jiaxin Ai, Fanrui Zhang, Yu Dai, Kaipeng Zhang • Category: cs.AI

Paper: http://arxiv.org/abs/2510.27410v1

Register: https://www.AiFeta.com

AI HumanAI Collaboration Socratic InformationTheory Entropy Dialogue LLMs UX Research ArXiv DiagramGeneration

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

GDPR compliance is more than checkboxes. A new roadmap from the Privatech project shows how automation and machine learning can help companies and law firms assess—and even generate—privacy compliance. * Shift the focus to data processors’ real workflows: drafting policies, mapping data uses, documenting decisions. * Break compliance into machine-ready

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Deep learning drives image search, robots, and medical scans. Most systems lean on CPUs and GPUs. This review asks: what if we run convolutional neural networks (CNNs) on FPGAs—reconfigurable chips you can tailor to the model? * Why FPGAs: custom dataflows, low latency, and strong energy efficiency—great for cameras,

Dynamic-K: Recommendations That Know When to Stop

Most apps show a fixed number of “top” items—say 10 movies or 20 products—assuming there are always enough good options. But that’s not always true: sometimes there are few relevant items, or some users are extra picky. The result? Filler recommendations. Dynamic-K flips the script. Instead of

Teaching chatbots to stop contradicting themselves (DECODE)

Teaching chatbots to stop contradicting themselves Ever had a bot say one thing, then the opposite a few turns later? This study introduces DECODE—a new task and dataset for spotting contradictions in everyday conversations, drawn from both human-human and human-bot chats. * New data beats existing natural language inference (NLI)

TL;DR

Read more

Automating GDPR Compliance: A Roadmap for Companies and Law Firms

FPGAs for Faster, Leaner Deep Learning: A Review of CNN Accelerators

Dynamic-K: Recommendations That Know When to Stop

Teaching chatbots to stop contradicting themselves (DECODE)