# LLM-Human Pipeline for Cultural Context Grounding of Conversations

arXiv: https://arxiv.org/abs/2410.13727 · HTML: https://mlsanity.com/paper/2410.13727/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 17 Oct 2024.

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

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them](https://mlsanity.com/paper/2210.09261/) (2022)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Aligning AI With Shared Human Values](https://mlsanity.com/paper/2008.02275/) (2020)
- [e-SNLI: Natural Language Inference with Natural Language Explanations](https://mlsanity.com/paper/1812.01193/) (2018)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://mlsanity.com/paper/1905.12516/) (2019)
- [Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets](https://mlsanity.com/paper/1908.07898/) (2019)
- [Why think step by step? Reasoning emerges from the locality of experience](https://mlsanity.com/paper/2304.03843/) (2023)
- [Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings](https://mlsanity.com/paper/1904.01596/) (2019)
- [NormBank: A Knowledge Bank of Situational Social Norms](https://mlsanity.com/paper/2305.17008/) (2023)
- [NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly](https://mlsanity.com/paper/2210.08604/) (2022)
- [Grounding 'Grounding' in NLP](https://mlsanity.com/paper/2106.02192/) (2021)
- [CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI](https://mlsanity.com/paper/2205.14727/) (2022)
- [NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation](https://mlsanity.com/paper/2310.14563/) (2023)
- [Assessing and Verifying Task Utility in LLM-Powered Applications](https://mlsanity.com/paper/2405.02178/) (2024)
- [Interactive Concept Learning for Uncovering Latent Themes in Large Text Collections](https://mlsanity.com/paper/2305.05094/) (2023)
- [Blind Spots and Biases: Exploring the Role of Annotator Cognitive Biases in NLP](https://mlsanity.com/paper/2404.19071/) (2024)
- [DEUS: A Data-driven Approach to Estimate User Satisfaction in Multi-turn Dialogues](https://mlsanity.com/paper/2103.01287/) (2021)
- [Fr'echet Distance for Offline Evaluation of Information Retrieval Systems with Sparse Labels](https://mlsanity.com/paper/2401.17543/) (2024)
- [Gender Bias in Text: Labeled Datasets and Lexicons](https://mlsanity.com/paper/2201.08675/) (2022)
- ["We Demand Justice!": Towards Social Context Grounding of Political Texts](https://mlsanity.com/paper/2311.09106/) (2023)

## Built on by (most cited first, 2 of 2)

- [Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Bench](https://mlsanity.com/paper/2504.01127/) (2025)
- [AlignCultura: Towards Culturally Aligned Large Language Models?](https://mlsanity.com/paper/2604.19016/) (2026)

## Abstract (arXiv)

Conversations often adhere to well-understood social norms that vary across cultures. For example, while "addressing parents by name" is commonplace in the West, it is rare in most Asian cultures. Adherence or violation of such norms often dictates the tenor of conversations. Humans are able to navigate social situations requiring cultural awareness quite adeptly. However, it is a hard task for NLP models. In this paper, we tackle this problem by introducing a "Cultural Context Schema" for conversations. It comprises (1) conversational information such as emotions, dialogue acts, etc., and (2) cultural information such as social norms, violations, etc. We generate ~110k social norm and violation descriptions for ~23k conversations from Chinese culture using LLMs. We refine them using automated verification strategies which are evaluated against culturally aware human judgements. We organize these descriptions into meaningful structures we call "Norm Concepts", using an interactive human-in-loop framework. We ground the norm concepts and the descriptions in conversations using symbolic annotation. Finally, we use the obtained dataset for downstream tasks such as emotion, sentiment, and dialogue act detection. We show that it significantly improves the empirical performance.