# Language Model Evaluation Beyond Perplexity

arXiv: https://arxiv.org/abs/2106.00085 · HTML: https://mlsanity.com/paper/2106.00085/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 49 references that are in the map.
- First posted on arXiv 31 May 2021.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Cross-lingual Language Model Pretraining](https://mlsanity.com/paper/1901.07291/) (2019)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [Designing and Interpreting Probes with Control Tasks](https://mlsanity.com/paper/1909.03368/) (2019)
- [Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies](https://mlsanity.com/paper/1611.01368/) (2016)
- [Analysis Methods in Neural Language Processing: A Survey](https://mlsanity.com/paper/1812.08951/) (2018)
- [Adaptive Input Representations for Neural Language Modeling](https://mlsanity.com/paper/1809.10853/) (2018)
- [Colorless green recurrent networks dream hierarchically](https://mlsanity.com/paper/1803.11138/) (2018)
- [Regularizing and Optimizing LSTM Language Models](https://mlsanity.com/paper/1708.02182/) (2017)
- [Sparse Sequence-to-Sequence Models](https://mlsanity.com/paper/1905.05702/) (2019)
- [Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation](https://mlsanity.com/paper/2005.10283/) (2020)
- [Correcting Length Bias in Neural Machine Translation](https://mlsanity.com/paper/1808.10006/) (2018)
- [Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information](https://mlsanity.com/paper/1808.08079/) (2018)
- [Improved Natural Language Generation via Loss Truncation](https://mlsanity.com/paper/2004.14589/) (2020)
- [Deep RNNs Encode Soft Hierarchical Syntax](https://mlsanity.com/paper/1805.04218/) (2018)
- [Evaluating Computational Language Models with Scaling Properties of Natural Language](https://mlsanity.com/paper/1906.09379/) (2019)
- [A Neural Model of Adaptation in Reading](https://mlsanity.com/paper/1808.09930/) (2018)
- [Do Neural Nets Learn Statistical Laws behind Natural Language?](https://mlsanity.com/paper/1707.04848/) (2017)
- [Length bias in Encoder Decoder Models and a Case for Global Conditioning](https://mlsanity.com/paper/1606.03402/) (2016)

## Built on by (most cited first, 30 of 78)

- [How much do language models copy from their training data? Evaluating linguistic novelty in text generation using RAVEN](https://mlsanity.com/paper/2111.09509/) (2021)
- [Truncation Sampling as Language Model Desmoothing](https://mlsanity.com/paper/2210.15191/) (2022)
- [Language Model Behavior: A Comprehensive Survey](https://mlsanity.com/paper/2303.11504/) (2023)
- [Ghostbuster: Detecting Text Ghostwritten by Large Language Models](https://mlsanity.com/paper/2305.15047/) (2023)
- [Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2311.12351/) (2023)
- [Uncertainty in Natural Language Generation: From Theory to Applications](https://mlsanity.com/paper/2307.15703/) (2023)
- [What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability](https://mlsanity.com/paper/2305.11707/) (2023)
- [Coherence boosting: When your pretrained language model is not paying enough attention](https://mlsanity.com/paper/2110.08294/) (2021)
- [Emergent Representations of Program Semantics in Language Models Trained on Programs](https://mlsanity.com/paper/2305.11169/) (2023)
- [REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering](https://mlsanity.com/paper/2402.17497/) (2024)
- [Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models](https://mlsanity.com/paper/2408.00523/) (2024)
- [LMentry: A Language Model Benchmark of Elementary Language Tasks](https://mlsanity.com/paper/2211.02069/) (2022)
- [Position: Key Claims in LLM Research Have a Long Tail of Footnotes](https://mlsanity.com/paper/2308.07120/) (2023)
- [Evaluating Distributional Distortion in Neural Language Modeling](https://mlsanity.com/paper/2203.12788/) (2022)
- [N-Best Hypotheses Reranking for Text-To-SQL Systems](https://mlsanity.com/paper/2210.10668/) (2022)
- [Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMs](https://mlsanity.com/paper/2410.15956/) (2024)
- [Measuring Data](https://mlsanity.com/paper/2212.05129/) (2022)
- [Meaning Representations from Trajectories in Autoregressive Models](https://mlsanity.com/paper/2310.18348/) (2023)
- [Semantic Compression With Large Language Models](https://mlsanity.com/paper/2304.12512/) (2023)
- [Confounding Factors in Relating Model Performance to Morphology](https://mlsanity.com/paper/2511.01380/) (2025)
- [Predictions from language models for multiple-choice tasks are not robust under variation of scoring methods](https://mlsanity.com/paper/2403.00998/) (2024)
- [Probing BERT's priors with serial reproduction chains](https://mlsanity.com/paper/2202.12226/) (2022)
- [The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?](https://mlsanity.com/paper/2601.07220/) (2026)
- [ChatGPT in the Age of Generative AI and Large Language Models: A Concise Survey](https://mlsanity.com/paper/2307.04251/) (2023)
- [What do Language Models Learn and When? The Implicit Curriculum Hypothesis](https://mlsanity.com/paper/2604.08510/) (2026)
- [Large Models of What? Mistaking Engineering Achievements for Human Linguistic Agency](https://mlsanity.com/paper/2407.08790/) (2024)
- [GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models](https://mlsanity.com/paper/2408.12494/) (2024)
- [The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation](https://mlsanity.com/paper/2412.04318/) (2024)
- [CPopQA: Ranking Cultural Concept Popularity by LLMs](https://mlsanity.com/paper/2311.07897/) (2023)
- [The GPT-WritingPrompts Dataset: A Comparative Analysis of Character Portrayal in Short Stories](https://mlsanity.com/paper/2406.16767/) (2024)

## Abstract (arXiv)

We propose an alternate approach to quantifying how well language models learn natural language: we ask how well they match the statistical tendencies of natural language. To answer this question, we analyze whether text generated from language models exhibits the statistical tendencies present in the human-generated text on which they were trained. We provide a framework--paired with significance tests--for evaluating the fit of language models to these trends. We find that neural language models appear to learn only a subset of the tendencies considered, but align much more closely with empirical trends than proposed theoretical distributions (when present). Further, the fit to different distributions is highly-dependent on both model architecture and generation strategy. As concrete examples, text generated under the nucleus sampling scheme adheres more closely to the type--token relationship of natural language than text produced using standard ancestral sampling; text from LSTMs reflects the natural language distributions over length, stopwords, and symbols surprisingly well.