mlsanityData to 7 Oct 2026

Emotional RAG LLMs: Reading Comprehension for the Open Internet

arXiv 2408.11189 ↗First posted 20 Aug 2024cs.CL cs.AI cs.IRcited by 1

Not on the map. Why?

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 42 references that are in the map. First posted on arXiv 20 Aug 2024.

Builds on

20 of 42 references.

References · 20

  1. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  4. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  5. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  6. 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 479
  7. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 246
  8. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  9. 2024Certifiably Robust RAG against Retrieval Corruptioncited by 144
  10. 2018Style Transfer Through Back-Translationcited by 124
  11. 2021GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrievalcited by 119
  12. 2020Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESuppositioncited by 76
8 more
  1. 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
  2. 2022A fine-grained comparison of pragmatic language understanding in humans and language modelscited by 69
  3. 2017A Large Self-Annotated Corpus for Sarcasmcited by 63
  4. 2019Evaluating Style Transfer for Textcited by 59
  5. 2022The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMscited by 57
  6. 2019iSarcasm: A Dataset of Intended Sarcasmcited by 39
  7. 2016A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networkscited by 33
  8. 2019Domain Adaptive Text Style Transfercited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026TEMPER: Testing Emotional Perturbation in Quantitative Reasoningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Reading with Intent -- Neutralizing Intent
  2. 2026Combining Retrieval-Augmented Text Generation with LLMs for Reading Content Recommendations
  3. 2024RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
  4. 2025RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance
  5. 2026TA-RAG: Tone Awareness as a Design Imperative for Retrieval-Augmented Generation
  6. 2024RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems
  7. 2025Out of Style: RAG's Fragility to Linguistic Variation
  8. 2025Evaluating the Effect of Retrieval Augmentation on Social Biases