# CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering

arXiv: https://arxiv.org/abs/2310.09536 · HTML: https://mlsanity.com/paper/2310.09536/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 14 Oct 2023.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Ignore Previous Prompt: Attack Techniques For Language Models](https://mlsanity.com/paper/2211.09527/) (2022)
- [Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLP](https://mlsanity.com/paper/2212.14024/) (2022)
- [SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking](https://mlsanity.com/paper/2107.05720/) (2021)
- [Leveraging Large Language Models for Multiple Choice Question Answering](https://mlsanity.com/paper/2210.12353/) (2022)
- [GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models](https://mlsanity.com/paper/2203.07281/) (2022)
- [Language Model Cascades](https://mlsanity.com/paper/2207.10342/) (2022)
- [From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective](https://mlsanity.com/paper/2205.04733/) (2022)
- [Few-Shot Text Generation with Pattern-Exploiting Training](https://mlsanity.com/paper/2012.11926/) (2020)
- [An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation](https://mlsanity.com/paper/1607.05368/) (2016)
- [Conversational Question Answering: A Survey](https://mlsanity.com/paper/2106.00874/) (2021)
- [FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference](https://mlsanity.com/paper/2212.08153/) (2022)
- [Probabilistic FastText for Multi-Sense Word Embeddings](https://mlsanity.com/paper/1806.02901/) (2018)
- [DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation](https://mlsanity.com/paper/2204.09149/) (2022)
- [Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search](https://mlsanity.com/paper/2202.06212/) (2022)

## Built on by (most cited first, 10 of 10)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review](https://mlsanity.com/paper/2506.06301/) (2025)
- [Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks](https://mlsanity.com/paper/2408.01433/) (2024)
- [LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks](https://mlsanity.com/paper/2409.12580/) (2024)
- [Performance Characterization of Expert Router for Scalable LLM Inference](https://mlsanity.com/paper/2404.15153/) (2024)
- [Tapping in a Remote Vehicle's onboard LLM to Complement the Ego Vehicle's Field-of-View](https://mlsanity.com/paper/2408.10794/) (2024)
- [Automated Factual Benchmarking for In-Car Conversational Systems using Large Language Models](https://mlsanity.com/paper/2504.01248/) (2025)
- [LoCar: Localization-Aware Evaluation of In-Vehicle Assistants through Fine-Grained Sociolinguistic Control](https://mlsanity.com/paper/2605.21086/) (2026)
- [Towards Systematic Qualification of Vision-Language Models for Automotive Perception Systems](https://mlsanity.com/paper/2609.25945/) (2026)
- [Automated Evaluation of Multi-Turn Dialogues in In-Car Conversational Assistants](https://mlsanity.com/paper/2609.35812/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated remarkable performance by following natural language instructions without fine-tuning them on domain-specific tasks and data. However, leveraging LLMs for domain-specific question answering suffers from severe limitations. The generated answer tends to hallucinate due to the training data collection time (when using off-the-shelf), complex user utterance and wrong retrieval (in retrieval-augmented generation). Furthermore, due to the lack of awareness about the domain and expected output, such LLMs may generate unexpected and unsafe answers that are not tailored to the target domain. In this paper, we propose CarExpert, an in-car retrieval-augmented conversational question-answering system leveraging LLMs for different tasks. Specifically, CarExpert employs LLMs to control the input, provide domain-specific documents to the extractive and generative answering components, and controls the output to ensure safe and domain-specific answers. A comprehensive empirical evaluation exhibits that CarExpert outperforms state-of-the-art LLMs in generating natural, safe and car-specific answers.