# Emotional RAG LLMs: Reading Comprehension for the Open Internet

arXiv: https://arxiv.org/abs/2408.11189 · HTML: https://mlsanity.com/paper/2408.11189/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 20 Aug 2024.

## Builds on (most cited first, 20 of 20)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer](https://mlsanity.com/paper/2110.07139/) (2021)
- [Certifiably Robust RAG against Retrieval Corruption](https://mlsanity.com/paper/2405.15556/) (2024)
- [Style Transfer Through Back-Translation](https://mlsanity.com/paper/1804.09000/) (2018)
- [GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval](https://mlsanity.com/paper/2112.07577/) (2021)
- [Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition](https://mlsanity.com/paper/2004.03066/) (2020)
- [Unsupervised Text Style Transfer using Language Models as Discriminators](https://mlsanity.com/paper/1805.11749/) (2018)
- [A fine-grained comparison of pragmatic language understanding in humans and language models](https://mlsanity.com/paper/2212.06801/) (2022)
- [A Large Self-Annotated Corpus for Sarcasm](https://mlsanity.com/paper/1704.05579/) (2017)
- [Evaluating Style Transfer for Text](https://mlsanity.com/paper/1904.02295/) (2019)
- [The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs](https://mlsanity.com/paper/2210.14986/) (2022)
- [iSarcasm: A Dataset of Intended Sarcasm](https://mlsanity.com/paper/1911.03123/) (2019)
- [A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1610.08815/) (2016)
- [Domain Adaptive Text Style Transfer](https://mlsanity.com/paper/1908.09395/) (2019)

## Built on by (most cited first, 1 of 1)

- [TEMPER: Testing Emotional Perturbation in Quantitative Reasoning](https://mlsanity.com/paper/2604.07801/) (2026)

## Abstract (arXiv)

Queries to large language models (LLMs) can be divided into two parts: the instruction/question and the accompanying context. The context for retrieval-augmented generation (RAG) systems in most benchmarks comes from Wikipedia-like texts written in a neutral and factual tone. However, real-world RAG applications often retrieve internet-based text with diverse tones and linguistic styles, posing challenges for downstream tasks. This paper introduces (a) a dataset that transforms RAG-retrieved passages into emotionally inflected and sarcastic text, (b) an emotion translation model for adapting text to different tones, and (c) a prompt-based method to improve LLMs' pragmatic interpretation of retrieved text.