arXiv AI
WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 24
WildTrace: Benchmarking Natural Evidence Trails in Long-Context Reasoning
arXiv:2607. 09328v2 Announce Type: replace-cross Abstract: Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages.
arXiv AI
Jul 13
WILDTRACE: Benchmarking Natural Evidence Trails in Long-Context Reasoning
arXiv:2607. 09328v1 Announce Type: cross Abstract: Answering complex questions over long documents frequently requires integrating evidence that the source itself disperses naturally across distant passages.
arXiv AI
3d ago
Trapped in Your Story: Evaluating Narrative-Induced Sycophancy in Large Language Models
Large language models (LLMs) tend to exhibit sycophancy by aligning with users’ expressed views. This study introduces a benchmark of 5,500 evaluation instances built from 500 debatable questions across ten domains, where the user stance is fixed but the justification is systematically varied across eleven conditions, including neutral, personal experience, causal framing, and worldview-based synthesis. Seven LLMs were evaluated, revealing that narrative structure can significantly influence agreement, with causal framing and bullet presentation boosting sycophancy while personal experience can reduce it.
arXiv Computation and Language
Aug 27
ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long Narratives
ClueWeaver is a dual-agent framework designed to enable compact, locally deployable language models to answer questions about long literary narratives. The Finder agent retrieves passages that contain answer-critical clues, while the Interpreter agent derives the answer from those passages, generates rationales with paragraph-ID citations, and performs self-calibration for high-risk questions. Both agents are trained with reward-guided reinforcement learning to prioritize evidence retention, correctness, grounding, and concise explanations, resulting in improved performance and inspectability over end-to-end prompting.
arXiv AI
Jun 6
Narrative Knowledge Weaver: Narrative-Centric Retrieval-Augmented Reasoning for Long-Form Text Understanding
arXiv:2606. 05724v1 Announce Type: cross Abstract: Long-form narrative QA requires reasoning over evolving story worlds rather than isolated passages: answers may depend on earlier goals, changing character states, social relations, causal triggers, temporal position, and later consequences.
arXiv Computation and Language
Sep 1
EVAR: Evidence-Validated Hypothesis Admission for Budget-Aware Narrative Reasoning
arXiv:2608.29835v1 Announce Type: new Abstract: Large language models (LLMs) often produce fluent but weakly grounded conclusions when reasoning over non-interactive, long-form narratives. A central...