# Critical Inker: Scaffolding Critical Thinking in AI-Assisted Writing Through Socratic Questioning

arXiv: https://arxiv.org/abs/2604.07167 · HTML: https://mlsanity.com/paper/2604.07167/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 4 of its 42 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 4 of 4)

- [Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task](https://mlsanity.com/paper/2506.08872/) (2025)
- [Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation](https://mlsanity.com/paper/2503.23363/) (2025)
- [Dialogues with AI Reduce Beliefs in Misinformation but Build No Lasting Discernment Skills](https://mlsanity.com/paper/2510.01537/) (2025)
- [IntelliProof: An Argumentation Network-based Conversational Helper for Organized Reflection](https://mlsanity.com/paper/2511.04528/) (2025)

## Built on by (most cited first, 1 of 1)

- [Agents That Teach: Towards Designing Incidental Learning Back into AI-Assisted Software Development](https://mlsanity.com/paper/2607.06101/) (2026)

## Abstract (arXiv)

As Large Language Models (LLMs) increasingly automate writing tasks, there is a growing risk of cognitive deskilling where users offload critical thinking to the system. To address this, we introduce Critical Inker, a writing tool designed to scaffold critical reflection during writing through logical analysis and socratic feedback. We present two methods: (1) A Socratic chatbot using questions to help them realize and fix logical errors in their writing and (2) Visual Feedback, which highlights logical errors in the text without dialog. We detail the technical implementation of the system and evaluate its argument extraction and logical validity accuracy. Our evaluation shows a 91.2% argument overlap with ground truth argument annotations and 87% validity accuracy. Finally, we conducted a small-scale pilot and discuss early qualitative results.