EmoLASP: Emotion Recognition with Language Models and Answer Set Programming

August 29, 2026 Β· Grace Period Β· πŸ› EMNLP 2026 Main Conference

⏳ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Thao Le, Michael Thielscher arXiv ID 2608.29035 Category cs.AI: Artificial Intelligence Cross-listed cs.CL Citations 0 Venue EMNLP 2026 Main Conference
Abstract
Emotion recognition in conversations is increasingly tackled with language models, but these models can be unstable and expensive to fine-tune or to prompt with long dialogue histories. We propose EmoLASP, a framework that combines a language model with declarative reasoning via Answer Set Programming (ASP) to predict VAD scores (Valence-Arousal-Dominance) in conversations. Experiments on a widely used benchmark dataset (IEMOCAP) across six open-source LLMs (3B-120B) and two PLMs (BERT, RoBERTa) show that EmoLASP improves prediction performance compared to using the language model alone, even when the LLMs/PLMs are given no dialogue history in their prompts or input vectors. The gains are largest for prompt-only LLMs, which EmoLASP uses without any fine-tuning. However, for fine-tuned PLMs, the reasoner adds little once dialogue history is available. EmoLASP's LLM pipeline demonstrates the potential advantages of using a reasoning approach to ensure emotion prediction consistency and to reduce both the cost of fine-tuning and the cost of prompting with long dialogue histories.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence