Practice and Challenges in Building a Business-oriented Search Engine Quality Metric

Chen, Nuo; Park, Donghyun; Park, H.W.; Choi, Ki-Bo; Sakai, Tetsuya; Kim, Jin‐Young

doi:10.1145/3539618.3591841

Cited by 1 publication

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Online methods rely on users' implicit or explicit online signals (such as A/B tests, click models [20], time-based models [80,87], machine learning based methods [16,35,67,97], etc.) as feedback to measure the effectiveness of IR systems, which goes beyond the main scope of this article.…”

Section: The Evaluation Of Information Retrieval Systemsmentioning

confidence: 99%

A study of the motivation of clerical officers in the Hong Kong Polytechnic University

張元妹¹

View full text Add to dashboard Cite

Automatic fact-checking plays a crucial role in combating the spread of misinformation. Large Language Models (LLMs) and Instruction-Following variants, such as InstructGPT and Alpaca, have shown remarkable performance in various natural language processing tasks. However, their knowledge may not always be up-to-date or sufficient, potentially leading to inaccuracies in fact-checking. To address this limitation, we propose combining the power of instruction-following language models with external evidence retrieval to enhance fact-checking performance. Our approach involves leveraging search engines to retrieve relevant evidence for a given input claim. This external evidence serves as valuable supplementary information to augment the knowledge of the pretrained language model. Then, we instruct-tune an open-sourced language model, called LLaMA, using this evidence, enabling it to predict the veracity of the input claim more accurately. To evaluate our method, we conducted experiments on two widely used fact-checking datasets: RAWFC and LIAR. The results demonstrate that our approach achieves state-of-the-art performance in fact-checking tasks. By integrating external evidence, we bridge the gap between the model's knowledge and the most up-to-date and sufficient context available, leading to improved fact-checking outcomes. Our findings have implications for combating misinformation and promoting the dissemination of accurate information on online platforms. Our released materials are accessible at: https://thcheung.github.io/factllama.

show abstract

Section: The Evaluation Of Information Retrieval Systemsmentioning

confidence: 99%

A study of the motivation of clerical officers in the Hong Kong Polytechnic University

張元妹¹

View full text Add to dashboard Cite

show abstract

Practice and Challenges in Building a Business-oriented Search Engine Quality Metric

Cited by 1 publication

References 30 publications

A study of the motivation of clerical officers in the Hong Kong Polytechnic University

A study of the motivation of clerical officers in the Hong Kong Polytechnic University

Contact Info

Product

Resources

About