long-form-text

EAVer introduces an end-to-end agentic policy for verifying facts in long-form text by grouping claims, efficiently searching, and reusing evidence, achieving superior performance on benchmarks like VeriFastScore and FaStFact-Bench with fewer searches.

MultiGhostBench is a multilingual benchmark for long-form LLM-generated text attribution under distribution shifts, featuring 928 books in six languages and highlighting performance degrades and no single method consistently best across settings.

ElementCheck is a complexity-aware framework that improves long-form text factuality evaluation by extracting sentence elements and organizing them into an element graph, accompanied by the new benchmark FastFact-Sent for enhanced verification accuracy.

Introduces Narrative Knowledge Weaver (NKW), a source-grounded framework for narrative-centric retrieval-augmented reasoning in long-form text understanding. It aligns textual evidence, atomic facts, graph structure, entity profiles, and storylines, achieving strong results on screenplay-level story-world QA benchmarks.