Say Less, Mean Better: Training-Free Verbosity Control for Language Models
cs.CL
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 16 pages, 11 figures
Code: https://github.com/MinimalLM/minimal-lm
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Phi-4 Technical Report
- The Llama 3 Herd of Models
- Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators
- Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking
- LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference
- Mistral 7B
- From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline
- RoBERTa: A Robustly Optimized BERT Pretraining Approach
- SlimInfer: Accelerating Long-Context LLM Inference via Dynamic Token Pruning
- Qwen2.5 Technical Report
- Verbosity Bias in Preference Labeling by Large Language Models
- A Long Way to Go: Investigating Length Correlations in RLHF
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data