# Chiaroscuro for Emotions: A Contrastive Emotion Benchmark Grounded in Appraisal Theory

arXiv: https://arxiv.org/abs/2609.03394 · HTML: https://mlsanity.com/paper/2609.03394/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 60 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification](https://mlsanity.com/paper/2010.12421/) (2020)
- [COSMIC: COmmonSense knowledge for eMotion Identification in Conversations](https://mlsanity.com/paper/2010.02795/) (2020)
- [Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts](https://mlsanity.com/paper/1906.01267/) (2019)
- [EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis](https://mlsanity.com/paper/2205.01996/) (2022)
- [Recognizing Emotion Cause in Conversations](https://mlsanity.com/paper/2012.11820/) (2020)
- [EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis](https://mlsanity.com/paper/2401.08508/) (2024)
- [XED: A Multilingual Dataset for Sentiment Analysis and Emotion Detection](https://mlsanity.com/paper/2011.01612/) (2020)
- [BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages](https://mlsanity.com/paper/2502.11926/) (2025)
- [CULEMO: Cultural Lenses on Emotion -- Benchmarking LLMs for Cross-Cultural Emotion Understanding](https://mlsanity.com/paper/2503.10688/) (2025)
- [SemEval-2024 Task 3: Multimodal Emotion Cause Analysis in Conversations](https://mlsanity.com/paper/2405.13049/) (2024)
- [IEST: WASSA-2018 Implicit Emotions Shared Task](https://mlsanity.com/paper/1809.01083/) (2018)
- [Both Matter: Enhancing the Emotional Intelligence of Large Language Models without Compromising the General Intelligence](https://mlsanity.com/paper/2402.10073/) (2024)
- [SocialNLP EmotionX 2019 Challenge Overview: Predicting Emotions in Spoken Dialogues and Chats](https://mlsanity.com/paper/1909.07734/) (2019)
- [Beyond Context to Cognitive Appraisal: Emotion Reasoning as a Theory of Mind Benchmark for Large Language Models](https://mlsanity.com/paper/2506.00334/) (2025)
- [Emo Pillars: Knowledge Distillation to Support Fine-Grained Context-Aware and Context-Less Emotion Classification](https://mlsanity.com/paper/2504.16856/) (2025)
- [Do Emotions Influence Moral Judgment in Large Language Models?](https://mlsanity.com/paper/2604.19125/) (2026)

## Abstract (arXiv)

Emotion recognition benchmarks often predict one emotion per text, missing many real-world scenarios where two people arrive at opposing emotions from a single shared event. For example, a child kicks the seat in front of her in excitement while the passenger ahead grows angry. We introduce CHIARO, a 1,000 human-annotated sentence benchmark for contrastive emotion inference grounded in appraisal theory. Each scene describes one causal trigger eliciting a positive emotion in one person and a negative emotion in the other, drawn from a ten-class taxonomy. We benchmark seven frontier LLMs and four off-the-shelf emotion classifiers. The strongest LLM reaches 67.3 macro-F1, well below human agreement, while existing emotion classifiers score near chance. Beyond evaluation, CHIARO also serves as a training signal. When combined with an existing emotion corpus, the resulting downstream classifier improves on CHIARO itself and on six of ten external emotion benchmarks, which positions our dataset as a complementary signal for emotion recognition.