# Which Prompts Make The Difference? Data Prioritization For Efficient Human LLM Evaluation

arXiv: https://arxiv.org/abs/2310.14424 · HTML: https://mlsanity.com/paper/2310.14424/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 82 references that are in the map.
- First posted on arXiv 22 Oct 2023.

## Builds on (most cited first, 30 of 49)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [The NarrativeQA Reading Comprehension Challenge](https://mlsanity.com/paper/1712.07040/) (2017)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance](https://mlsanity.com/paper/1909.02622/) (2019)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations](https://mlsanity.com/paper/2110.05719/) (2021)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [A Study of BFLOAT16 for Deep Learning Training](https://mlsanity.com/paper/1905.12322/) (2019)
- [Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models](https://mlsanity.com/paper/2111.02840/) (2021)
- [Fine-tuning language models to find agreement among humans with diverse preferences](https://mlsanity.com/paper/2211.15006/) (2022)
- [SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualization](https://mlsanity.com/paper/2212.10465/) (2022)
- [Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics](https://mlsanity.com/paper/2006.06264/) (2020)
- [RankME: Reliable Human Ratings for Natural Language Generation](https://mlsanity.com/paper/1803.05928/) (2018)

## Built on by (most cited first, 18 of 18)

- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning](https://mlsanity.com/paper/2402.06619/) (2024)
- [The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm](https://mlsanity.com/paper/2406.18682/) (2024)
- [Elo Uncovered: Robustness and Best Practices in Language Model Evaluation](https://mlsanity.com/paper/2311.17295/) (2023)
- [To Code, or Not To Code? Exploring Impact of Code in Pre-training](https://mlsanity.com/paper/2408.10914/) (2024)
- [RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs](https://mlsanity.com/paper/2407.02552/) (2024)
- [Language Imbalance Driven Rewarding for Multilingual Self-improving](https://mlsanity.com/paper/2410.08964/) (2024)
- [Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition](https://mlsanity.com/paper/2404.08008/) (2024)
- [On the Limitations of Compute Thresholds as a Governance Strategy](https://mlsanity.com/paper/2407.05694/) (2024)
- [Critical Learning Periods: Leveraging Early Training Dynamics for Efficient Data Pruning](https://mlsanity.com/paper/2405.19462/) (2024)
- [The Future of Open Human Feedback](https://mlsanity.com/paper/2408.16961/) (2024)
- [The Multilingual Divide and Its Impact on Global AI Safety](https://mlsanity.com/paper/2505.21344/) (2025)
- [How Reliable is Language Model Micro-Benchmarking?](https://mlsanity.com/paper/2510.08730/) (2025)
- [LLM See, LLM Do: Guiding Data Generation to Target Non-Differentiable Objectives](https://mlsanity.com/paper/2407.01490/) (2024)
- [Engagement-Driven Content Generation with Large Language Models](https://mlsanity.com/paper/2411.13187/) (2024)
- [Compare without Despair: Reliable Preference Evaluation with Generation Separability](https://mlsanity.com/paper/2407.01878/) (2024)
- [Decoding Alignment: A Critical Survey of LLM Development Initiatives through Value-setting and Data-centric Lens](https://mlsanity.com/paper/2508.16982/) (2025)
- [Invent a Dataset: Measuring dataset generation abilities with zero seed](https://mlsanity.com/paper/2610.01674/) (2026)

## Abstract (arXiv)

Human evaluation is increasingly critical for assessing large language models, capturing linguistic nuances, and reflecting user preferences more accurately than traditional automated metrics. However, the resource-intensive nature of this type of annotation process poses significant challenges. The key question driving our work: "is it feasible to minimize human-in-the-loop feedback by prioritizing data instances which most effectively distinguish between models?" We evaluate several metric-based methods and find that these metrics enhance the efficiency of human evaluations by minimizing the number of required annotations, thus saving time and cost, while ensuring a robust performance evaluation. We show that our method is effective across widely used model families, reducing instances of indecisive (or "tie") outcomes by up to 54% compared to a random sample when focusing on the top-20 percentile of prioritized instances. This potential reduction in required human effort positions our approach as a valuable strategy in future large language model evaluations.