Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge

The paper introduces ElephantBench, a closed‑book knowledge probe with 1,094 multi‑account factual questions generated via an auditable graph‑based pipeline that pulls documents from a low‑exposure web corpus and identifies naturally occurring disagreements. Across 32 large language models, even the best model only recovers both divergent accounts on 52.4% of questions, and most models recall one account while omitting the other, indicating persistent epistemic myopia. The study shows that scaling model size and inference‑time reasoning improves recall but does not eliminate incompleteness, and that exposure imbalance in the corpus biases models toward the dominant account.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

• llms
• nlp
• benchmarks