Alignment has a Fantasia Problem
cs.AI, cs.HC
Submitted: 2026-04-23
Updated: 2026-09-25
Project page: https://lovable.dev
Terminology
Sources
- LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models
- STaR-GATE: Teaching Language Models to Ask Clarifying Questions
- Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
- Exploring Prompt Engineering Practices in the Enterprise
- Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following
- Language Models (Mostly) Know What They Know
- Active Task Disambiguation with LLMs
- Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task
- CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models
- Feedforward in Generative AI: Opportunities for a Design Space
- User Misconceptions of LLM-Based Conversational Programming Assistants
- Probing Early Modification of Gravity with Planck, ACT and SPT
- The Prompt Report: A Systematic Survey of Prompt Engineering Techniques
- Proximal Policy Optimization Algorithms
- Navigating Rifts in Human-LLM Grounding: Study and Benchmark
- Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
- Completion $\neq$ Collaboration: Scaling Collaborative Effort with Agents
- Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection