{"url":"/task/triviaqa","name":"TriviaQA","slug":"triviaqa","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":124,"papers_with_code":60,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/triviaqa-on-big-bench","slug":"triviaqa-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Gopher-280B (few-shot, k=64)","paper_title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","paper_url":"/paper/scaling-language-models-methods-analysis-1","paper_date":"2021-12-08","arxiv_id":"2112.11446","code_links":[{"title":"allenai/dolma","url":"https://github.com/allenai/dolma"},{"title":"rvlopes/gloria","url":"https://github.com/rvlopes/gloria"},{"title":"bramiozo/PubScience","url":"https://github.com/bramiozo/PubScience"}],"syntology":null}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[{"url":"/task/general-knowledge","name":"General Knowledge"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":60,"tagged_in_all":124,"items":[{"url":"/paper/longformer-the-long-document-transformer","title":"Longformer: The Long-Document Transformer","date":"2020-04-10","arxiv_id":"2004.05150","repositories_listed":22,"syntology":{"n":35,"n_ran":15,"n_unverified":20,"n_pointer_only":5}},{"url":"/paper/leveraging-passage-retrieval-with-generative","title":"Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering","date":"2020-07-02","arxiv_id":"2007.01282","repositories_listed":8,"syntology":null},{"url":"/paper/knowledge-guided-text-retrieval-and-reading","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","date":"2019-11-10","arxiv_id":"1911.03868","repositories_listed":7,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/relevance-guided-supervision-for-openqa-with","title":"Relevance-guided Supervision for OpenQA with ColBERT","date":"2020-07-01","arxiv_id":"2007.00814","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/triviaqa-a-large-scale-distantly-supervised","title":"TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension","date":"2017-05-09","arxiv_id":"1705.03551","repositories_listed":3,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/lacie-listener-aware-finetuning-for","title":"LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models","date":"2024-05-31","arxiv_id":"2405.21028","repositories_listed":2,"syntology":null},{"url":"/paper/end-to-end-training-of-neural-retrievers-for","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","date":"2021-01-02","arxiv_id":"2101.00408","repositories_listed":2,"syntology":null},{"url":"/paper/genki-enhancing-open-domain-question","title":"GenKI: Enhancing Open-Domain Question Answering with Knowledge Integration and Controllable Generation in Large Language Models","date":"2025-05-26","arxiv_id":"2505.19660","repositories_listed":1,"syntology":null},{"url":"/paper/dragonverseqa-open-domain-long-form-context","title":"DragonVerseQA: Open-Domain Long-Form Context-Aware Question-Answering","date":"2024-12-21","arxiv_id":"2412.16694","repositories_listed":1,"syntology":null},{"url":"/paper/kv-prediction-for-improved-time-to-first","title":"KV Prediction for Improved Time to First Token","date":"2024-10-10","arxiv_id":"2410.08391","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-hint-generation-approaches-in-open","title":"Exploring Hint Generation Approaches in Open-Domain Question Answering","date":"2024-09-24","arxiv_id":"2409.16096","repositories_listed":1,"syntology":null},{"url":"/paper/fastfid-improve-inference-efficiency-of-open","title":"FastFiD: Improve Inference Efficiency of Open Domain Question Answering via Sentence Selection","date":"2024-08-12","arxiv_id":"2408.06333","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/from-artificial-needles-to-real-haystacks","title":"From Artificial Needles to Real Haystacks: Improving Retrieval Capabilities in LLMs by Finetuning on Synthetic Data","date":"2024-06-27","arxiv_id":"2406.19292","repositories_listed":1,"syntology":null},{"url":"/paper/judging-the-judges-evaluating-alignment-and","title":"Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges","date":"2024-06-18","arxiv_id":"2406.12624","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/cram-credibility-aware-attention-modification","title":"CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAG","date":"2024-06-17","arxiv_id":"2406.11497","repositories_listed":1,"syntology":null},{"url":"/paper/re-rag-improving-open-domain-qa-performance","title":"RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation","date":"2024-06-09","arxiv_id":"2406.05794","repositories_listed":1,"syntology":null},{"url":"/paper/retaining-key-information-under-high","title":"Retaining Key Information under High Compression Ratios: Query-Guided Compressor for LLMs","date":"2024-06-04","arxiv_id":"2406.02376","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/accurate-and-nuanced-open-qa-evaluation","title":"Accurate and Nuanced Open-QA Evaluation Through Textual Entailment","date":"2024-05-26","arxiv_id":"2405.16702","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/layer-skip-enabling-early-exit-inference-and","title":"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding","date":"2024-04-25","arxiv_id":"2404.16710","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":5}},{"url":"/paper/multi-granularity-guided-fusion-in-decoder","title":"Multi-Granularity Guided Fusion-in-Decoder","date":"2024-04-03","arxiv_id":"2404.02581","repositories_listed":1,"syntology":null},{"url":"/paper/harnessing-multi-role-capabilities-of-large","title":"Harnessing Multi-Role Capabilities of Large Language Models for Open-Domain Question Answering","date":"2024-03-08","arxiv_id":"2403.05217","repositories_listed":1,"syntology":null},{"url":"/paper/unfamiliar-finetuning-examples-control-how","title":"Unfamiliar Finetuning Examples Control How Language Models Hallucinate","date":"2024-03-08","arxiv_id":"2403.05612","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":7}},{"url":"/paper/a-bias-variance-covariance-decomposition-of","title":"A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models","date":"2023-10-09","arxiv_id":"2310.05833","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/generator-retriever-generator-a-novel","title":"Generator-Retriever-Generator Approach for Open-Domain Question Answering","date":"2023-07-21","arxiv_id":"2307.11278","repositories_listed":1,"syntology":null},{"url":"/paper/rfid-towards-rational-fusion-in-decoder-for","title":"RFiD: Towards Rational Fusion-in-Decoder for Open-Domain Question Answering","date":"2023-05-26","arxiv_id":"2305.17041","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-abstract-meaning-representation","title":"Exploiting Abstract Meaning Representation for Open-Domain Question Answering","date":"2023-05-26","arxiv_id":"2305.17050","repositories_listed":1,"syntology":null},{"url":"/paper/beamsearchqa-large-language-models-are-strong","title":"Allies: Prompting Large Language Model with Beam Search","date":"2023-05-24","arxiv_id":"2305.14766","repositories_listed":1,"syntology":{"n":13,"n_ran":1,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/just-ask-for-calibration-strategies-for","title":"Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedback","date":"2023-05-24","arxiv_id":"2305.14975","repositories_listed":1,"syntology":null},{"url":"/paper/critic-large-language-models-can-self-correct","title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing","date":"2023-05-19","arxiv_id":"2305.11738","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}