Attribute First, then Generate: Locally-attributable Grounded Text Generation
Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections. Yet, these citations often point to entire documents or paragraphs, burdening users with extensive verification work. In this paper, we introduce a locally-attributable text generation approach, prioritizing concise attributions. Our method, named "Attribute First, then Generate", breaks down the conventional end-to-end generation process into three intuitive steps: content selection, sentence planning, and sequential sentence generation. By initially identifying relevant source segments ("select first") and then conditioning the generation process on them ("then generate"), we ensure these segments also act as the output's fine-grained attributions ("select" becomes "attribute"). Tested on Multi-document Summarization and Long-form Question-answering, our method not only yields more concise citations than the baselines but also maintains - and in some cases enhances - both generation quality and attribution accuracy. Furthermore, it significantly reduces the time required for fact verification by human assessors.
Code (1)
Tasks
AttributeDocument SummarizationFact CheckingFact VerificationLong Form Question AnsweringMulti-Document SummarizationQuestion AnsweringSentenceText GenerationSimilar Papers 제목 키워드 기반
Evaluating Attribution in Dialogue Systems: The BEGIN Benchmark
Knowledge-grounded dialogue systems powered by large language models often generate responses that, while fluent, are not attributable to a relevant source of information. Progress towards models that do not exhibit this…
Language ModellingNatural Language InferenceThink Before You Attribute: Improving the Performance of LLMs Attribution Systems
Large Language Models (LLMs) are increasingly applied in various science domains, yet their broader adoption remains constrained by a critical challenge: the lack of trustworthy, verifiable outputs. Current LLMs often ge…
AttributeRAGSentenceAdversarial Attack Attribution: Discovering Attributable Signals in Adversarial ML Attacks
Machine Learning (ML) models are known to be vulnerable to adversarial inputs and researchers have demonstrated that even production systems, such as self-driving cars and ML-as-a-service offerings, are susceptible. Thes…
Adversarial AttackAttributeSelf-Driving CarsShape-aware Generative Adversarial Networks for Attribute Transfer
Generative adversarial networks (GANs) have been successfully applied to transfer visual attributes in many domains, including that of human face images. This success is partly attributable to the facts that human faces …
AttributeImage-to-Image TranslationTransfer LearningTranslationLocalizing Factual Inconsistencies in Attributable Text Generation
There has been an increasing interest in detecting hallucinations in model-generated texts, both manually and automatically, at varying levels of granularity. However, most existing methods fail to precisely pinpoint the…
Text Generation