14 citations · 30 across the 10 of their papers we have counts for
7 papers · 1 filter
Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization
Jan Drchal
Large language models (LLMs) are often asked to produce JSON conforming to a fixed schema, powering information extraction, tool calling, agentic planning, and knowledge-graph cons…
AIC CTU@AVerImaTeC: dual-retriever RAG for image-text fact checking
Herbert Ullrich, Jan Drchal
In this paper, we present our 3rd place system in the AVerImaTeC shared task, which combines our last year's retrieval-augmented generation (RAG) pipeline with a reverse image sear…
AIC CTU@FEVER 8: On-premise fact checking through long context RAG
Herbert Ullrich, Jan Drchal
In this paper, we present our fact-checking pipeline which has scored first in FEVER 8 shared task. Our fact-checking system is a simple two-step RAG pipeline based on our last yea…
Claim Extraction for Fact-Checking: Data, Models, and Automated Metrics
Herbert Ullrich, Tomáš Mlynář, Jan Drchal
In this paper, we explore the problem of Claim Extraction using one-to-many text generation methods, comparing LLMs, small summarization models finetuned for the task, and a previo…
AIC CTU system at AVeriTeC: Re-framing automated fact-checking as a simple RAG task
Herbert Ullrich, Tomáš Mlynář, Jan Drchal
This paper describes our place submission in the AVeriTeC shared task in which we attempted to address the challenge of fact-checking with evidence retrieved in the wild u…
Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language
Jan Drchal, Herbert Ullrich, Tomáš Mlynář +1
This article presents a pipeline for automated fact-checking leveraging publicly available Language Models and data. The objective is to assess the accuracy of textual claims using…
CsFEVER and CTKFacts: Acquiring Czech data for fact verification
Herbert Ullrich, Jan Drchal, Martin Rýpar +2
In this paper, we examine several methods of acquiring Czech data for automated fact-checking, which is a task commonly modeled as a classification of textual claim veracity w.r.t.…