# LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue

arXiv: https://arxiv.org/abs/2210.07777 · HTML: https://mlsanity.com/paper/2210.07777/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 14 Oct 2022.

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

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift](https://mlsanity.com/paper/2003.04475/) (2020)
- [GuessWhat?! Visual object discovery through multi-modal dialogue](https://mlsanity.com/paper/1611.08481/) (2016)
- [Tighter risk certificates for neural networks](https://mlsanity.com/paper/2007.12911/) (2020)
- [A survey on domain adaptation theory: learning bounds and theoretical guarantees](https://mlsanity.com/paper/2004.11829/) (2020)
- [Theoretical Analysis of Domain Adaptation with Optimal Transport](https://mlsanity.com/paper/1610.04420/) (2016)
- [Support and Invertibility in Domain-Invariant Representations](https://mlsanity.com/paper/1903.03448/) (2019)
- [Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.06585/) (2017)
- [Unsupervised Domain Adaptation Based on Source-guided Discrepancy](https://mlsanity.com/paper/1809.03839/) (2018)
- [End-to-end optimization of goal-driven and visually grounded dialogue systems](https://mlsanity.com/paper/1703.05423/) (2017)
- [PAC-Bayes and Domain Adaptation](https://mlsanity.com/paper/1707.05712/) (2017)
- [Beyond task success: A closer look at jointly learning to see, ask, and GuessWhat](https://mlsanity.com/paper/1809.03408/) (2018)
- [PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners](https://mlsanity.com/paper/2207.05685/) (2022)
- [The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error](https://mlsanity.com/paper/2203.11317/) (2022)
- [COSMic: A Coherence-Aware Generation Metric for Image Descriptions](https://mlsanity.com/paper/2109.05281/) (2021)
- [Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights](https://mlsanity.com/paper/2207.07255/) (2022)

## Built on by (most cited first, 4 of 4)

- [Learning to Generate Equitable Text in Dialogue from Biased Training Data](https://mlsanity.com/paper/2307.04303/) (2023)
- [Measuring How (Not Just Whether) VLMs Build Common Ground](https://mlsanity.com/paper/2509.03805/) (2025)
- [HumBEL: A Human-in-the-Loop Approach for Evaluating Demographic Factors of Language Models in Human-Machine Conversations](https://mlsanity.com/paper/2305.14195/) (2023)
- [Dialogue with Robots: Proposals for Broadening Participation and Research in the SLIVAR Community](https://mlsanity.com/paper/2404.01158/) (2024)

## Abstract (arXiv)

Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor theoretical understanding of the objectives in text-generation and their relation to the learning process (i.e., model training). To this end, we propose a new theoretical framework for learning to generate text in dialogue. Compared to existing theories of learning, our framework allows for analysis of the multi-faceted goals inherent to text-generation. We use our framework to develop theoretical guarantees for learners that adapt to unseen data. As an example, we apply our theory to study data-shift within a cooperative learning algorithm proposed for the GuessWhat?! visual dialogue game. From this insight, we propose a new algorithm, and empirically, we demonstrate our proposal improves both task-success and human-likeness of the generated text. Finally, we show statistics from our theory are empirically predictive of multiple qualities of the generated dialogue, suggesting our theory is useful for model-selection when human evaluations are not available.