Lune

ACL Findings2025

Speech Act Patterns for Improving Generalizability of Explainable Politeness Detection Models

Ahmad Aljanaideh

Abstract

The lack of explainability in state-of-the-art Natural Language Understanding (NLU) classification models has increased interest in developing techniques for improving explainable linear feature-based models (e.g., Logistic Regression/SVM). Politeness detection is a task that exemplifies this interest. While those techniques perform well on the task when applied to data from the same domain as the training data, they lack generalizability and thus fall short when applied to data from other domains. This is due to their reliance on discovering domainspecific word-level features. We introduce a method for improving the generalizability of explainable politeness models by relying on speech act patterns instead of words, leveraging speech act labels assigned by the GPT-4 model. This approach goes beyond the mere words and injects intent into politeness classification models, enhancing their generalizability. Results demonstrate that the proposed method achieves state-of-the-art accuracy in the cross-domain setting among explainable methods, while falling short in the in-domain setting. Our findings illustrate that explainable models can benefit from Large Language Models.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Deberta: decoding-Enhanced Bert with Disentangled Attention cites Language Models are Few-Shot Learners
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on3

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Deberta: decoding-Enhanced Bert with Disentangled AttentionPengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu ChenICLR 2021 · 3,729 citations
  3. Dual Process Masking for Dialogue Act RecognitionYeo Jin Kim, Halim Acosta, Wookhee Min, Jonathan P. Rowe et al.EMNLP Findings 2024 · 5 citations

Related papers

  1. LLM-induced Rationales for More Compact Explainable Style Classification ModelsAhmad Aljanaideh, Saeb GanidehACL Findings 2026
  2. "My life is miserable, have to sign 500 autographs everyday": Exposing Humblebragging, the Brags in DisguiseSharath Naganna, Saprativa Bhattacharjee, Biplab Banerjee, Pushpak BhattacharyyaACL Findings 2025 · 2 citations
  3. LLMs for Generating and Evaluating Counterfactuals: A Comprehensive StudyVan Bach Nguyen, Paul Youssef, Christin Seifert, Jörg SchlöttererEMNLP Findings 2024 · 11 citations
  4. Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social RelationshipsDavid Jurgens, Agrima Seth, Jackson Sargent, Athena Aghighi et al.ACL 2023 · 4 citations
  5. Navigating the Unknown: Intent Classification and Out-of-Distribution Detection Using Large Language ModelsYusuf Sali, Sitki Can ToramanEMNLP Findings 2025 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines