# Evaluating Human-LLM Representation Alignment: A Case Study on Affective Sentence Generation for Augmentative and Alternative Communication

arXiv: https://arxiv.org/abs/2503.11881 · HTML: https://mlsanity.com/paper/2503.11881/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 69 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Plan-And-Write: Towards Better Automatic Storytelling](https://mlsanity.com/paper/1811.05701/) (2018)
- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [MojiTalk: Generating Emotional Responses at Scale](https://mlsanity.com/paper/1711.04090/) (2017)
- [An empirical study of LLaMA3 quantization: from LLMs to MLLMs](https://mlsanity.com/paper/2404.14047/) (2024)
- [Affect-LM: A Neural Language Model for Customizable Affective Text Generation](https://mlsanity.com/paper/1704.06851/) (2017)
- [Affect-Driven Dialog Generation](https://mlsanity.com/paper/1904.02793/) (2019)
- [Sequence to Backward and Forward Sequences: A Content-Introducing Approach to Generative Short-Text Conversation](https://mlsanity.com/paper/1607.00970/) (2016)
- [Enhancing Emotional Generation Capability of Large Language Models via Emotional Chain-of-Thought](https://mlsanity.com/paper/2401.06836/) (2024)
- [EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model](https://mlsanity.com/paper/2501.05710/) (2025)
- [Affective Computing in the Era of Large Language Models: A Survey from the NLP Perspective](https://mlsanity.com/paper/2408.04638/) (2024)
- [Adapting a Language Model for Controlled Affective Text Generation](https://mlsanity.com/paper/2011.04000/) (2020)
- [Learning Norms from Stories: A Prior for Value Aligned Agents](https://mlsanity.com/paper/1912.03553/) (2019)
- [EmoMix: Emotion Mixing via Diffusion Models for Emotional Speech Synthesis](https://mlsanity.com/paper/2306.00648/) (2023)
- [Taking Principles Seriously: A Hybrid Approach to Value Alignment](https://mlsanity.com/paper/2012.11705/) (2020)
- [Enhancing Empathetic Response Generation by Augmenting LLMs with Small-scale Empathetic Models](https://mlsanity.com/paper/2402.11801/) (2024)
- [Show Me How To Revise: Improving Lexically Constrained Sentence Generation with XLNet](https://mlsanity.com/paper/2109.05797/) (2021)
- [Customizing Large Language Model Generation Style using Parameter-Efficient Finetuning](https://mlsanity.com/paper/2409.04574/) (2024)
- [Fine-grained Sentiment Controlled Text Generation](https://mlsanity.com/paper/2006.09891/) (2020)
- [Enhancing Cognitive Models of Emotions with Representation Learning](https://mlsanity.com/paper/2104.10117/) (2021)
- [Lexical Complexity Controlled Sentence Generation](https://mlsanity.com/paper/2211.14540/) (2022)
- [Controlling keywords and their positions in text generation](https://mlsanity.com/paper/2304.09516/) (2023)
- [Aging Up AAC: An Introspection on Augmentative and Alternative Communication Applications for Autistic Adults](https://mlsanity.com/paper/2404.17730/) (2024)
- [Emotion-Aware Embedding Fusion in LLMs (Flan-T5, LLAMA 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation](https://mlsanity.com/paper/2410.01306/) (2024)
- [LLM-based Affective Text Generation Quality Based on Different Quantization Values](https://mlsanity.com/paper/2501.19317/) (2025)

## Built on by (most cited first, 1 of 1)

- [How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study](https://mlsanity.com/paper/2604.00005/) (2026)

## Abstract (arXiv)

Gaps arise between a language model's use of concepts and people's expectations. This gap is critical when LLMs generate text to help people communicate via Augmentative and Alternative Communication (AAC) tools. In this work, we introduce the evaluation task of Representation Alignment for measuring this gap via human judgment. In our study, we expand keywords and emotion representations into full sentences. We select four emotion representations: Words, Valence-Arousal-Dominance (VAD) dimensions expressed in both Lexical and Numeric forms, and Emojis. In addition to Representation Alignment, we also measure people's judgments of the accuracy and realism of the generated sentences. While representations like VAD break emotions into easy-to-compute components, our findings show that people agree more with how LLMs generate when conditioned on English words (e.g., "angry") rather than VAD scales. This difference is especially visible when comparing Numeric VAD to words. Furthermore, we found that the perception of how much a generated sentence conveys an emotion is dependent on both the representation type and which emotion it is.