TriviaQA

TriviaQA is a dataset that contains a collection of trivia questions and their corresponding answers, used to evaluate the factual correctness of answer generation in large language model systems.

Papers using TriviaQA (12)

Benchmarking Prompt Sensitivity in Large Language Models2025 · 2 citesMultiHaluDet: Multilingual Hallucination Detection via LLM Hidden State Probing2026PersonalAI: A Systematic Comparison of Knowledge Graph Storage and Retrieval Approaches for Personalized LLM agents2026PersonalAI 2.0: Enhancing knowledge graph traversal/retrieval with planning mechanism for Personalized LLM Agents2026Calibrating LLMs with Semantic-level Reward2026How do LLMs Compute Verbal Confidence2026HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering2025MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination2025Optimizing Knowledge Integration in Retrieval-Augmented Generation with Self-Selection2025Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation2024LLMs are Biased Evaluators But Not Biased for Retrieval Augmented Generation2024Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation2024