Exploring Semantic Filtering Heuristics For Efficient Claim Verification
Given the limited computational and financial resources of news agencies, real-life usage of fact-checking systems requires fast response times. For this reason, our submission to the FEVER-8 claim verification shared task focuses on optimizing the efficiency of such pipelines built around subtasks such as evi dence retrieval and veracity prediction. We pro pose the Semantic Filtering for Efficient Fact Checking (SFEFC) strategy, which is inspired by the FEVER-8 baseline and designed with the goal of reducing the number of LLM calls and other computationally expensive subrou tines. Furthermore, we explore the reuse of cosine similarities initially calculated within a dense retrieval step to retrieve the top 10 most relevant evidence sentence sets. We use these sets for semantic filtering methods based on similarity scores and create filters for particularly hard classification labels “Not Enough Information” and “Conflicting Evi dence/Cherrypicking” by identifying thresh olds for potentially relevant information and the semantic variance within these sets. Com pared to the parallelized FEVER-8 baseline, which takes 33.88 seconds on average to pro cess a claim according to the FEVER-8 shared task leaderboard, our non-parallelized system remains competitive in regard to AVeriTeC re trieval scores while reducing the runtime to 7.01 seconds, achieving the fastest average runtime per claim.
