# textitDial BeInfo for Faithfulness: Improving Factuality of Information-Seeking Dialogue via Behavioural Fine-Tuning

arXiv: https://arxiv.org/abs/2311.09800 · HTML: https://mlsanity.com/paper/2311.09800/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 44 references that are in the map.
- First posted on arXiv 16 Nov 2023.

## Builds on (most cited first, 30 of 31)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies](https://mlsanity.com/paper/1804.11283/) (2018)
- [Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering](https://mlsanity.com/paper/2307.16877/) (2023)
- [On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?](https://mlsanity.com/paper/2204.07931/) (2022)
- [FaithDial: A Faithful Benchmark for Information-Seeking Dialogue](https://mlsanity.com/paper/2204.10757/) (2022)
- [Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding](https://mlsanity.com/paper/2104.08455/) (2021)
- [A Dataset for Document Grounded Conversations](https://mlsanity.com/paper/1809.07358/) (2018)
- [TopiOCQA: Open-domain Conversational Question Answering with Topic Switching](https://mlsanity.com/paper/2110.00768/) (2021)
- [Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations](https://mlsanity.com/paper/2308.11995/) (2023)
- [Interpretation of Natural Language Rules in Conversational Machine Reading](https://mlsanity.com/paper/1809.01494/) (2018)
- [Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features](https://mlsanity.com/paper/2107.06963/) (2021)
- [Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access](https://mlsanity.com/paper/2006.03533/) (2020)
- [MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents](https://mlsanity.com/paper/2109.12595/) (2021)
- [DoQA -- Accessing Domain-Specific FAQs via Conversational QA](https://mlsanity.com/paper/2005.01328/) (2020)
- [Contrastive Learning Reduces Hallucination in Conversations](https://mlsanity.com/paper/2212.10400/) (2022)
- [Elastic Weight Removal for Faithful and Abstractive Dialogue Generation](https://mlsanity.com/paper/2303.17574/) (2023)
- [Learning to Relate to Previous Turns in Conversational Search](https://mlsanity.com/paper/2306.02553/) (2023)
- [Can Pretrained Language Models (Yet) Reason Deductively?](https://mlsanity.com/paper/2210.06442/) (2022)

## Built on by (most cited first, 9 of 9)

- [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Factuality of Large Language Models: A Survey](https://mlsanity.com/paper/2402.02420/) (2024)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)
- [Mitigating Large Language Model Hallucination with Faithful Finetuning](https://mlsanity.com/paper/2406.11267/) (2024)
- [Constructing Benchmarks and Interventions for Combating Hallucinations in LLMs](https://mlsanity.com/paper/2404.09971/) (2024)
- [Distinguishing Ignorance from Error in LLM Hallucinations](https://mlsanity.com/paper/2410.22071/) (2024)
- [Empowering Air Travelers: A Chatbot for Canadian Air Passenger Rights](https://mlsanity.com/paper/2403.12678/) (2024)
- [HalluClean: A Unified Framework to Combat Hallucinations in LLMs](https://mlsanity.com/paper/2511.08916/) (2025)

## Abstract (arXiv)

Factuality is a crucial requirement in information seeking dialogue: the system should respond to the user's queries so that the responses are meaningful and aligned with the knowledge provided to the system. However, most modern large language models suffer from hallucinations, that is, they generate responses not supported by or contradicting the knowledge source. To mitigate the issue and increase faithfulness of information-seeking dialogue systems, we introduce BeInfo, a simple yet effective method that applies behavioural tuning to aid information-seeking dialogue. Relying on three standard datasets, we show that models tuned with BeInfo} become considerably more faithful to the knowledge source both for datasets and domains seen during BeInfo-tuning, as well as on unseen domains, when applied in a zero-shot manner. In addition, we show that the models with 3B parameters (e.g., Flan-T5) tuned with BeInfo demonstrate strong performance on data from real `production' conversations and outperform GPT4 when tuned on a limited amount of such realistic in-domain dialogues.