Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
cs.AI
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/QxLabIreland/ReChat
Terminology
Sources
- ChatGPT and U(X): A Rapid Review on Measuring the User Experience
- LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agents
- Lost in the Middle: How Language Models Use Long Contexts
- LLMs Get Lost In Multi-Turn Conversation
- Recursively Summarizing Books with Human Feedback
- Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Ignore Previous Prompt: Attack Techniques For Language Models
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