Surprising efficacy of fine-tuned transformers for fact-checking over larger language models

V Setty - Proceedings of the 47th International ACM SIGIR …, 2024 - dl.acm.org
In this paper, we explore the challenges associated with establishing an end-to-end fact-
checking pipeline in a real-world context, covering over 90 languages. Our real-world …

Claim verification in the age of large language models: A survey

A Dmonte, R Oruche, M Zampieri, P Calyam… - arxiv preprint arxiv …, 2024 - arxiv.org
The large and ever-increasing amount of data available on the Internet coupled with the
laborious task of manual claim and fact verification has sparked the interest in the …

QuestGen: Effectiveness of Question Generation Methods for Fact-Checking Applications

R Setty, V Setty - Proceedings of the 33rd ACM International Conference …, 2024 - dl.acm.org
Verifying fact-checking claims poses a significant challenge, even for humans. Recent
approaches have demonstrated that decomposing claims into relevant questions to gather …

MAIR: A Massive Benchmark for Evaluating Instructed Retrieval

W Sun, Z Shi, J Wu, L Yan, X Ma, Y Liu, M Cao… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent information retrieval (IR) models are pre-trained and instruction-tuned on massive
datasets and tasks, enabling them to perform well on a wide range of tasks and potentially …

EXPLORA: Efficient Exemplar Subset Selection for Complex Reasoning

K Purohit, R Devalla, KM Yerragorla… - arxiv preprint arxiv …, 2024 - arxiv.org
Answering reasoning-based complex questions over text and hybrid sources, including
tables, is a challenging task. Recent advances in large language models (LLMs) have …

FactIR: A Real-World Zero-shot Open-Domain Retrieval Benchmark for Fact-Checking

V Setty - arxiv preprint arxiv:2502.06006, 2025 - arxiv.org
The field of automated fact-checking increasingly depends on retrieving web-based
evidence to determine the veracity of claims in real-world scenarios. A significant challenge …