# On the probability-quality paradox in language generation

arXiv: https://arxiv.org/abs/2203.17217 · HTML: https://mlsanity.com/paper/2203.17217/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [All That's 'Human' Is Not Gold: Evaluating Human Evaluation of Generated Text](https://mlsanity.com/paper/2107.00061/) (2021)
- [Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation](https://mlsanity.com/paper/2005.10283/) (2020)
- [On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behavior](https://mlsanity.com/paper/2006.01912/) (2020)
- [If beam search is the answer, what was the question?](https://mlsanity.com/paper/2010.02650/) (2020)
- [On NMT Search Errors and Model Errors: Cat Got Your Tongue?](https://mlsanity.com/paper/1908.10090/) (2019)
- [Trading Off Diversity and Quality in Natural Language Generation](https://mlsanity.com/paper/2004.10450/) (2020)
- [On Decoding Strategies for Neural Text Generators](https://mlsanity.com/paper/2203.15721/) (2022)
- [Comparison of Diverse Decoding Methods from Conditional Language Models](https://mlsanity.com/paper/1906.06362/) (2019)
- [Consistency of a Recurrent Language Model With Respect to Incomplete Decoding](https://mlsanity.com/paper/2002.02492/) (2020)
- [A surprisal--duration trade-off across and within the world's languages](https://mlsanity.com/paper/2109.15000/) (2021)
- [Decoding Methods for Neural Narrative Generation](https://mlsanity.com/paper/2010.07375/) (2020)
- [How (Non-)Optimal is the Lexicon?](https://mlsanity.com/paper/2104.14279/) (2021)
- [A Cognitive Regularizer for Language Modeling](https://mlsanity.com/paper/2105.07144/) (2021)
- [Mirostat: A Neural Text Decoding Algorithm that Directly Controls Perplexity](https://mlsanity.com/paper/2007.14966/) (2020)

## Built on by (most cited first, 16 of 16)

- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [Truncation Sampling as Language Model Desmoothing](https://mlsanity.com/paper/2210.15191/) (2022)
- [Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation](https://mlsanity.com/paper/2206.02369/) (2022)
- [Probing the Creativity of Large Language Models: Can models produce divergent semantic association?](https://mlsanity.com/paper/2310.11158/) (2023)
- [On the Efficacy of Sampling Adapters](https://mlsanity.com/paper/2307.03749/) (2023)
- [The Stable Entropy Hypothesis and Entropy-Aware Decoding: An Analysis and Algorithm for Robust Natural Language Generation](https://mlsanity.com/paper/2302.06784/) (2023)
- [Best-k Search Algorithm for Neural Text Generation](https://mlsanity.com/paper/2211.11924/) (2022)
- [Language Model Decoding as Likelihood-Utility Alignment](https://mlsanity.com/paper/2210.07228/) (2022)
- [Quantifying the perceptual value of lexical and non-lexical channels in speech](https://mlsanity.com/paper/2307.03534/) (2023)
- [On the Typicality of Musical Sequences](https://mlsanity.com/paper/2211.13016/) (2022)
- [Generative transformations and patterns in LLM-native approaches for software verification and falsification](https://mlsanity.com/paper/2404.09384/) (2024)
- [Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?](https://mlsanity.com/paper/2605.28778/) (2026)
- [Express Your Doubts -- Probabilistic World Modeling Should not be Based on Token logprobs](https://mlsanity.com/paper/2505.02072/) (2025)
- [Entropy-Aligned Decoding of LMs for Better Writing and Reasoning](https://mlsanity.com/paper/2601.01714/) (2026)
- [Metacognition in LLMs: Foundations, Progress, and Opportunities](https://mlsanity.com/paper/2607.11881/) (2026)
- [IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG](https://mlsanity.com/paper/2210.13829/) (2022)

## Abstract (arXiv)

When generating natural language from neural probabilistic models, high probability does not always coincide with high quality: It has often been observed that mode-seeking decoding methods, i.e., those that produce high-probability text under the model, lead to unnatural language. On the other hand, the lower-probability text generated by stochastic methods is perceived as more human-like. In this note, we offer an explanation for this phenomenon by analyzing language generation through an information-theoretic lens. Specifically, we posit that human-like language should contain an amount of information (quantified as negative log-probability) that is close to the entropy of the distribution over natural strings. Further, we posit that language with substantially more (or less) information is undesirable. We provide preliminary empirical evidence in favor of this hypothesis; quality ratings of both human and machine-generated text -- covering multiple tasks and common decoding strategies -- suggest high-quality text has an information content significantly closer to the entropy than we would expect by chance.