# Alignment has a Fantasia Problem

arXiv: https://arxiv.org/abs/2604.21827 · HTML: https://mlsanity.com/paper/2604.21827/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 50 of its 80 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 30 of 50)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Cooperative Inverse Reinforcement Learning](https://mlsanity.com/paper/1606.03137/) (2016)
- [Do Large Language Models Know What They Don't Know?](https://mlsanity.com/paper/2305.18153/) (2023)
- [Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning](https://mlsanity.com/paper/2408.10075/) (2024)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [Personalized Language Modeling from Personalized Human Feedback](https://mlsanity.com/paper/2402.05133/) (2024)
- [CollabLLM: From Passive Responders to Active Collaborators](https://mlsanity.com/paper/2502.00640/) (2025)
- [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](https://mlsanity.com/paper/2406.06608/) (2024)
- [In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents](https://mlsanity.com/paper/2503.08026/) (2025)
- [Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task](https://mlsanity.com/paper/2506.08872/) (2025)
- [STaR-GATE: Teaching Language Models to Ask Clarifying Questions](https://mlsanity.com/paper/2403.19154/) (2024)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following](https://mlsanity.com/paper/2410.15553/) (2024)
- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing](https://mlsanity.com/paper/2309.09128/) (2023)
- [LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models](https://mlsanity.com/paper/2311.18232/) (2023)
- [MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models](https://mlsanity.com/paper/2401.16745/) (2024)
- [Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions](https://mlsanity.com/paper/2410.13788/) (2024)
- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models](https://mlsanity.com/paper/2212.07769/) (2022)

## Abstract (arXiv)

In accomplishing complex tasks, human cognition typically progresses from abstract to concrete (e.g., from brainstorming ideas to writing an essay). With the advent of highly capable AI assistants, people now offload various parts of their task to the system. However, instruction-tuned AI systems, even when designed to infer implicit intent, lack an understanding of humans' cognitive processes. When a user approaches AI while their goals and intentions are abstract, AI systems often short circuit their cognitive process through which those goals would be refined by jumping toward a final output (e.g., writing the essay entirely). Doing so takes away the user's agency in achieving the task: they may need to spend more time revising or, worse, settle on a suboptimal outcome. We call these failures Fantasia interactions after the famous Disney scene. We argue that Fantasia interactions demand a rethinking of alignment research, where AI systems optimize how cognitive responsibility is allocated within an interaction. We highlight gaps in state-of-the-art alignment methods, and outline a research agenda for training and evaluating models to achieve this vision.