# Improving Diversity in Language Models: When Temperature Fails, Change the Loss

arXiv: https://arxiv.org/abs/2508.09654 · HTML: https://mlsanity.com/paper/2508.09654/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 26 of 26)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [A note on the evaluation of generative models](https://mlsanity.com/paper/1511.01844/) (2015)
- [Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints](https://mlsanity.com/paper/2309.16240/) (2023)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [Aligning Language Models with Preferences through f-divergence Minimization](https://mlsanity.com/paper/2302.08215/) (2023)
- [Is Temperature the Creativity Parameter of Large Language Models?](https://mlsanity.com/paper/2405.00492/) (2024)
- [Improved Natural Language Generation via Loss Truncation](https://mlsanity.com/paper/2004.14589/) (2020)
- [Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models](https://mlsanity.com/paper/1701.03185/) (2017)
- [Exploring Precision and Recall to assess the quality and diversity of LLMs](https://mlsanity.com/paper/2402.10693/) (2024)
- [What Makes Large Language Models Reason in (Multi-Turn) Code Generation?](https://mlsanity.com/paper/2410.08105/) (2024)
- [Tailoring Language Generation Models under Total Variation Distance](https://mlsanity.com/paper/2302.13344/) (2023)
- [Inverse-RLignment: Large Language Model Alignment from Demonstrations through Inverse Reinforcement Learning](https://mlsanity.com/paper/2405.15624/) (2024)
- [Arrows of Time for Large Language Models](https://mlsanity.com/paper/2401.17505/) (2024)
- [Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows](https://mlsanity.com/paper/2305.18910/) (2023)
- [Optimal Budgeted Rejection Sampling for Generative Models](https://mlsanity.com/paper/2311.00460/) (2023)

## Built on by (most cited first, 7 of 7)

- [Where does output diversity collapse in post-training?](https://mlsanity.com/paper/2604.16027/) (2026)
- [Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR](https://mlsanity.com/paper/2510.08892/) (2025)
- [Training Large Language Models To Reason In Parallel With Global Forking Tokens](https://mlsanity.com/paper/2510.05132/) (2025)
- [Diversity in Large Language Models under Supervised Fine-Tuning](https://mlsanity.com/paper/2605.00195/) (2026)
- [Equalized Generative Treatment: Matching f-divergences for Fairness in Generative Models](https://mlsanity.com/paper/2602.08660/) (2026)
- [Quality-constrained Entropy Maximization Policy Optimization for LLM Diversity](https://mlsanity.com/paper/2602.15894/) (2026)
- [Entropy-Constrained Strategy Optimization in Urban Floods: A Multi-Agent Framework with LLM and Knowledge Graph Integration](https://mlsanity.com/paper/2508.14654/) (2025)

## Abstract (arXiv)

Increasing diversity in language models is a challenging yet essential objective. A common approach is to raise the decoding temperature. In this work, we investigate this approach through a simplistic yet common case to provide insights into why decreasing temperature can improve quality (Precision), while increasing it often fails to boost coverage (Recall). Our analysis reveals that for a model to be effectively tunable through temperature adjustments, it must be trained toward coverage. To address this, we propose rethinking loss functions in language models by leveraging the Precision-Recall framework. Our results demonstrate that this approach achieves a substantially better trade-off between Precision and Recall than merely combining negative log-likelihood training with temperature scaling. These findings offer a pathway toward more versatile and robust language modeling techniques.