# Do Chatbot LLMs Talk Too Much? The YapBench Benchmark

arXiv: https://arxiv.org/abs/2601.00624 · HTML: https://mlsanity.com/paper/2601.00624/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 2 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators](https://mlsanity.com/paper/2404.04475/) (2024)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Camels in a Changing Climate: Enhancing LM Adaptation with Tulu 2](https://mlsanity.com/paper/2311.10702/) (2023)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [Phi-4-reasoning Technical Report](https://mlsanity.com/paper/2504.21318/) (2025)
- [Verbosity Bias in Preference Labeling by Large Language Models](https://mlsanity.com/paper/2310.10076/) (2023)
- [Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2310.05199/) (2023)
- [How Hungry is AI? Benchmarking Energy, Water, and Carbon Footprint of LLM Inference](https://mlsanity.com/paper/2505.09598/) (2025)
- [Explaining Length Bias in LLM-Based Preference Evaluations](https://mlsanity.com/paper/2407.01085/) (2024)
- [Over-Reasoning and Redundant Calculation of Large Language Models](https://mlsanity.com/paper/2401.11467/) (2024)
- [Devstral: Fine-tuning Language Models for Coding Agent Applications](https://mlsanity.com/paper/2509.25193/) (2025)
- [Dissecting users' needs for search result explanations](https://mlsanity.com/paper/2401.16509/) (2024)
- [ConCISE: A Reference-Free Conciseness Evaluation Metric for LLM-Generated Answers](https://mlsanity.com/paper/2511.16846/) (2025)

## Built on by (most cited first, 5 of 5)

- [DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference](https://mlsanity.com/paper/2604.24647/) (2026)
- [GraphRAG for Engineering Diagrams: ChatP&ID Enables LLM Interaction with P&IDs](https://mlsanity.com/paper/2603.22528/) (2026)
- [Multilingual Multi-Label Emotion Classification at Scale with Synthetic Data](https://mlsanity.com/paper/2604.12633/) (2026)
- [Not What, But How: A Framework for Auditing LLM Responses across Positioning, Generalization, Anthropomorphism, and Maxims](https://mlsanity.com/paper/2606.02493/) (2026)
- [CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression](https://mlsanity.com/paper/2606.24083/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) such as ChatGPT, Claude, and Gemini increasingly act as general-purpose copilots, yet they often respond with unnecessary length on simple requests, adding redundant explanations, hedging, or boilerplate that increases cognitive load and inflates token-based inference cost. Prior work suggests that preference-based post-training and LLM-judged evaluations can induce systematic length bias, where longer answers are rewarded even at comparable quality. We introduce YapBench, a lightweight benchmark for quantifying user-visible over-generation on brevity-ideal prompts. Each item consists of a single-turn prompt, a curated minimal-sufficient baseline answer, and a category label. Our primary metric, YapScore, measures excess response length beyond the baseline in characters, enabling comparisons across models without relying on any specific tokenizer. We summarize model performance via the YapIndex, a uniformly weighted average of category-level median YapScores. YapBench contains over three hundred English prompts spanning three common brevity-ideal settings: (A) minimal or ambiguous inputs where the ideal behavior is a short clarification, (B) closed-form factual questions with short stable answers, and (C) one-line coding tasks where a single command or snippet suffices. Evaluating 76 assistant LLMs, we observe an order-of-magnitude spread in median excess length and distinct category-specific failure modes, including vacuum-filling on ambiguous inputs and explanation or formatting overhead on one-line technical requests. We release the benchmark and maintain a live leaderboard for tracking verbosity behavior over time.