How Decoding Strategies Affect the Verifiability of Generated Text
Recent progress in pre-trained language models led to systems that are able to generate text of an increasingly high quality. While several works have investigated the fluency and grammatical correctness of such models, it is still unclear to which extent the generated text is consistent with factual world knowledge. Here, we go beyond fluency and also investigate the verifiability of text generated by state-of-the-art pre-trained language models. A generated sentence is verifiable if it can be corroborated or disproved by Wikipedia, and we find that the verifiability of generated text strongly depends on the decoding strategy. In particular, we discover a tradeoff between factuality (i.e., the ability of generating Wikipedia corroborated text) and repetitiveness. While decoding strategies such as top-k and nucleus sampling lead to less repetitive generations, they also produce less verifiable text. Based on these finding, we introduce a simple and effective decoding strategy which, in comparison to previously used decoding strategies, produces less repetitive and more verifiable text.
Code (1)
Tasks
Language ModellingNatural Language UnderstandingSentenceWorld KnowledgeSimilar Papers 제목 키워드 기반
Energy-Conscious LLM Decoding: Impact of Text Generation Strategies on GPU Energy Consumption
Decoding strategies significantly influence the quality and diversity of the generated texts in large language models (LLMs), yet their impact on computational resource consumption, particularly GPU energy usage, is insu…
BenchmarkingCode SummarizationDiversityGPU+2How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study
As texts generated by Large Language Models (LLMs) are ever more common and often indistinguishable from human-written content, research on automatic text detection has attracted growing attention. Many recent detectors …
Text DetectionAssessing the Verifiability of Attributions in News Text
When reporting the news, journalists rely on the statements of stakeholders, experts, and officials. The attribution of such a statement is verifiable if its fidelity to the source can be confirmed or denied. In this pap…
Question AnsweringDiversifying to Verify: When Task-Equivalent Programs Differ in Verifiability
Program verification is crucial for software correctness, but producing fully verified programs remains difficult in practice. This paper studies whether implementation structure affects automated verifiability when mult…
ClearSight: Visual Signal Enhancement for Object Hallucination Mitigation in Multimodal Large language Models
Contrastive decoding strategies are widely used to mitigate object hallucinations in multimodal large language models (MLLMs). By reducing over-reliance on language priors, these strategies ensure that generated content …
Computational EfficiencyHallucinationObject Hallucination