# LinGO: A Linguistic Graph Optimization Framework with LLMs for Interpreting Intents of Online Uncivil Discourse

arXiv: https://arxiv.org/abs/2602.04693 · HTML: https://mlsanity.com/paper/2602.04693/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 4 Feb 2026.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [HateCheck: Functional Tests for Hate Speech Detection Models](https://mlsanity.com/paper/2012.15606/) (2020)
- [A BERT-Based Transfer Learning Approach for Hate Speech Detection in Online Social Media](https://mlsanity.com/paper/1910.12574/) (2019)
- [Challenges for Toxic Comment Classification: An In-Depth Error Analysis](https://mlsanity.com/paper/1809.07572/) (2018)
- [A Survey of Automatic Prompt Engineering: An Optimization Perspective](https://mlsanity.com/paper/2502.11560/) (2025)
- [LLM-AutoDiff: Auto-Differentiate Any LLM Workflow](https://mlsanity.com/paper/2501.16673/) (2025)
- [NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps](https://mlsanity.com/paper/2404.01651/) (2024)
- [Detecting Hate Speech and Offensive Language on Twitter using Machine Learning: An N-gram and TFIDF based Approach](https://mlsanity.com/paper/1809.08651/) (2018)
- [A Machine Learning Approach to Comment Toxicity Classification](https://mlsanity.com/paper/1903.06765/) (2019)
- [Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers](https://mlsanity.com/paper/2509.14266/) (2025)
- [Collaborative Human-AI Risk Annotation: Co-Annotating Online Incivility with CHAIRA](https://mlsanity.com/paper/2409.14223/) (2024)
- [Quantifying the Spread of Online Incivility in Brazilian Politics](https://mlsanity.com/paper/2504.08960/) (2025)

## Abstract (arXiv)

Detecting uncivil language is crucial for maintaining safe, inclusive, and democratic online spaces. Yet existing classifiers often misinterpret posts containing uncivil cues but expressing civil intents, leading to inflated estimates of harmful incivility online. We introduce LinGO, a linguistic graph optimization framework for large language models (LLMs) that leverages linguistic structures and optimization techniques to classify multi-class intents of incivility that use various direct and indirect expressions. LinGO decomposes language into multi-step linguistic components, identifies targeted steps that cause the most errors, and iteratively optimizes prompt and/or example components for targeted steps. We evaluate it using a dataset collected during the 2022 Brazilian presidential election, encompassing four forms of political incivility: Impoliteness (IMP), Hate Speech and Stereotyping (HSST), Physical Harm and Violent Political Rhetoric (PHAVPR), and Threats to Democratic Institutions and Values (THREAT). Each instance is annotated with six types of civil/uncivil intent. We benchmark LinGO using three cost-efficient LLMs: GPT-5-mini, Gemini 2.5 Flash-Lite, and Claude 3 Haiku, and four optimization techniques: TextGrad, AdalFlow, DSPy, and Retrieval-Augmented Generation (RAG). The results show that, across all models, LinGO consistently improves accuracy and weighted F1 compared with zero-shot, chain-of-thought, direct optimization, and fine-tuning baselines. RAG is the strongest optimization technique and, when paired with Gemini model, achieves the best overall performance. These findings demonstrate that incorporating multi-step linguistic components into LLM instructions and optimize targeted components can help the models explain complex semantic meanings, which can be extended to other complex semantic explanation tasks in the future.