FarFetched: An Entity-centric Approach for Reasoning on Textually Represented Environments
We address the problem of automatically acquiring knowledge from news articles and leverage it to estimate the veracity of a user's claim based on the supporting or refuting content within the accumulated evidence. We present FarFetched, an entity-centric approach for reasoning based on news, where latent connections between events, actions or statements are discovered via their identified entity mentions and are represented with the help of a knowledge graph. We propose a way of selecting specific subsets from the accumulated wealth of information based on the user hypothesis and construct relevant premises relying on the semantic similarity between them. We leverage textual entailment recognition to provide a measurable way for assessing whether the user claim is plausible based on the selected evidence. Our work is demonstrated on the less-resourced Greek language and supported by the training of state-of-the-art models for STS and NLI that are evaluated on benchmark datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
ArticlesNatural Language InferenceSemantic SimilaritySemantic Textual SimilaritySTSSimilar Papers 제목 키워드 기반
FarFetched: Entity-centric Reasoning and Claim Validation for the Greek Language based on Textually Represented Environments
Our collective attention span is shortened by the flood of online information. With \textit{FarFetched}, we address the need for automated claim validation based on the aggregated evidence derived from multiple online ne…
Entity LinkingNatural Language InferenceSemantic SimilaritySemantic Textual Similarity+1APEX-MEM: Agentic Semi-Structured Memory with Temporal Reasoning for Long-Term Conversational AI
Large language models still struggle with reliable long-term conversational memory: simply enlarging context windows or applying naive retrieval often introduces noise and destabilizes responses. We present APEX-MEM, a c…
Question AnsweringNarrativeTrack: Evaluating Entity-Centric Reasoning for Narrative Understanding
Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand temporally unfolding narratives in videos remains underexplored. True narrative und…
Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models
Vision-language models (VLMs) excel at extracting and reasoning about information from images. Yet, their capacity to leverage internal knowledge about specific entities remains underexplored. This work investigates the …
GATHER: Convergence-Centric Hyper-Entity Retrieval for Zero-Shot Cell-Type Annotation
Zero-shot single-cell cell-type annotation aims to determine a cell's type from a given set of expressed genes without any training. Existing knowledge-graph-based RAG approaches retrieve evidence by expanding from sourc…