Controlled Text Generation via Language Model Arithmetic

arXiv:2311.14479 · cs.CL · Submitted 2023-11-24 · Read on arXiv

cs.CL

Submitted: 2023-11-24

Updated: 2026-10-12

Code: https://github.com/eth-sri/language-model-arithmetic

Terminology

• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes

Sources

• Accelerating Large Language Model Decoding with Speculative Sampling
• Controllable Text Generation with Language Constraints
• PaLM: Scaling Language Modeling with Pathways
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
• GPT-4 Technical Report
• Code Llama: Open Foundation Models for Code
• Stay on topic with Classifier-Free Guidance
• GEDI: GEnerative and DIscriminative Training for Self-Supervised Learning
• Classifiers are Better Experts for Controllable Text Generation
• Release Strategies and the Social Impacts of Language Models
• Accelerating LLM Inference with Staged Speculative Decoding
• Llama 2: Open Foundation and Fine-Tuned Chat Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering