# Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features

arXiv: https://arxiv.org/abs/2107.06963 · HTML: https://mlsanity.com/paper/2107.06963/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 14 Jul 2021.

## Builds on (most cited first, 23 of 23)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation](https://mlsanity.com/paper/1603.08023/) (2016)
- [Faithful to the Original: Fact Aware Neural Abstractive Summarization](https://mlsanity.com/paper/1711.04434/) (2017)
- [What makes a good conversation? How controllable attributes affect human judgments](https://mlsanity.com/paper/1902.08654/) (2019)
- [A Knowledge-Grounded Neural Conversation Model](https://mlsanity.com/paper/1702.01932/) (2017)
- [Data-to-Text Generation with Content Selection and Planning](https://mlsanity.com/paper/1809.00582/) (2018)
- [Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data](https://mlsanity.com/paper/2010.05873/) (2020)
- [Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue](https://mlsanity.com/paper/2002.07510/) (2020)
- [Learning to Select Knowledge for Response Generation in Dialog Systems](https://mlsanity.com/paper/1902.04911/) (2019)
- [Polite Dialogue Generation Without Parallel Data](https://mlsanity.com/paper/1805.03162/) (2018)
- [Towards Exploiting Background Knowledge for Building Conversation Systems](https://mlsanity.com/paper/1809.08205/) (2018)
- [A Controllable Model of Grounded Response Generation](https://mlsanity.com/paper/2005.00613/) (2020)
- [The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents](https://mlsanity.com/paper/1911.03768/) (2019)
- [Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading](https://mlsanity.com/paper/1906.02738/) (2019)
- [Reducing Quantity Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2009.13312/) (2020)
- [Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation](https://mlsanity.com/paper/2005.06128/) (2020)

## Built on by (most cited first, 30 of 74)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment](https://mlsanity.com/paper/2308.05374/) (2023)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [Factuality Enhanced Language Models for Open-Ended Text Generation](https://mlsanity.com/paper/2206.04624/) (2022)
- [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)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [FaithDial: A Faithful Benchmark for Information-Seeking Dialogue](https://mlsanity.com/paper/2204.10757/) (2022)
- [What You See is What You Read? Improving Text-Image Alignment Evaluation](https://mlsanity.com/paper/2305.10400/) (2023)
- [Enhancing Uncertainty-Based Hallucination Detection with Stronger Focus](https://mlsanity.com/paper/2311.13230/) (2023)
- [Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback](https://mlsanity.com/paper/2306.00186/) (2023)
- [DialFact: A Benchmark for Fact-Checking in Dialogue](https://mlsanity.com/paper/2110.08222/) (2021)
- [Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation](https://mlsanity.com/paper/2405.15307/) (2024)
- [RHO (ρ): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding](https://mlsanity.com/paper/2212.01588/) (2022)
- [KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection](https://mlsanity.com/paper/2310.09044/) (2023)
- [mFACE: Multilingual Summarization with Factual Consistency Evaluation](https://mlsanity.com/paper/2212.10622/) (2022)
- [Opportunities and Challenges in Neural Dialog Tutoring](https://mlsanity.com/paper/2301.09919/) (2023)
- [Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning](https://mlsanity.com/paper/2305.15065/) (2023)
- [Diving Deep into Modes of Fact Hallucinations in Dialogue Systems](https://mlsanity.com/paper/2301.04449/) (2023)
- [Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation](https://mlsanity.com/paper/2110.05456/) (2021)
- [Elastic Weight Removal for Faithful and Abstractive Dialogue Generation](https://mlsanity.com/paper/2303.17574/) (2023)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [The Dangers of trusting Stochastic Parrots: Faithfulness and Trust in Open-domain Conversational Question Answering](https://mlsanity.com/paper/2305.16519/) (2023)
- [Multi-Stage Prompting for Knowledgeable Dialogue Generation](https://mlsanity.com/paper/2203.08745/) (2022)
- [Hallucination Detection and Hallucination Mitigation: An Investigation](https://mlsanity.com/paper/2401.08358/) (2024)
- [Improving Factual Consistency for Knowledge-Grounded Dialogue Systems via Knowledge Enhancement and Alignment](https://mlsanity.com/paper/2310.08372/) (2023)
- ["Why is this misleading?": Detecting News Headline Hallucinations with Explanations](https://mlsanity.com/paper/2302.05852/) (2023)
- [Gl'orIA -- A Generative and Open Large Language Model for Portuguese](https://mlsanity.com/paper/2402.12969/) (2024)
- [Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval](https://mlsanity.com/paper/2407.03585/) (2024)

## Abstract (arXiv)

Knowledge-grounded dialogue systems are intended to convey information that is based on evidence provided in a given source text. We discuss the challenges of training a generative neural dialogue model for such systems that is controlled to stay faithful to the evidence. Existing datasets contain a mix of conversational responses that are faithful to selected evidence as well as more subjective or chit-chat style responses. We propose different evaluation measures to disentangle these different styles of responses by quantifying the informativeness and objectivity. At training time, additional inputs based on these evaluation measures are given to the dialogue model. At generation time, these additional inputs act as stylistic controls that encourage the model to generate responses that are faithful to the provided evidence. We also investigate the usage of additional controls at decoding time using resampling techniques. In addition to automatic metrics, we perform a human evaluation study where raters judge the output of these controlled generation models to be generally more objective and faithful to the evidence compared to baseline dialogue systems.