Hugging Face's logo

Spaces:
CONDA-Workshop
/
Data-Contamination-Database
Running

App Files Community
29
Data-Contamination-Database / contamination_report.csv

Commit History

  1. Postprocessing

    OSainz
    998b5f7

  2. GPT-3.5 HumanEval_R CodeForces2305 contamination based on https://arxiv.org/abs/2402.15938 (#28)⁠

    OSainz +1: suryanshs16103
    Verified signature
    047d292

  3. Likely FLORES contamination for Claude 3 Opus (#29)⁠

    Iker +1: davidstap
    Verified signature
    52c7b2a

  1. Add reports from Benchmarking paper "Benchmark Leakage in Large Language Models" (#27)⁠

    OSainz +1: SinclairWang
    Verified signature
    25633c4

  1. Add Reports Based on "Llemma: An Open Language Model For Mathematics" (#23)⁠

    OSainz +1: wlchen
    Verified signature
    9fba4d8

  1. add flores contamination in xP3 (#20)⁠

    OSainz +1: davidstap
    Verified signature
    100cb5e

  1. Add Aquila model series which have gsm8k test set contamination (#21)⁠

    OSainz +1: bpHigh
    Verified signature
    8f6a7cc

  2. GPT-3.5 Spider contamination based on https://arxiv.org/pdf/2402.08100 (#18)⁠

    OSainz +1: bpHigh
    Verified signature
    dc4c3f8

  1. Updates

    OSainz
    d4d0c64

  2. Add changes

    OSainz
    23add19

  3. Superglue/RealNews Contamination based on "Noise-Robust De-Duplication at Scale" (#15)⁠

    OSainz +1: emilys
    Verified signature
    888fb82

  4. Mistral 7B Arc Easy Contamination based on "Proving Test Set Contamination in Black Box Language Models" (#14)⁠

    OSainz +1: AmeyaPrabhu
    Verified signature
    4f71313

  5. Added Contamination Evidence from GPT4 Tech Report using String matching on GPT-4 (#11)⁠

    OSainz +1: AmeyaPrabhu
    Verified signature
    f82db5d

  6. GPT-3.5Turbo HumanEval Contamination based on "Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models" (#16)⁠

    OSainz +1: jupyter31
    Verified signature
    6b722ae

  7. Added Contamination Evidence on MMLU of ChatGPT/GPT4 from "Investigating data contamination in modern benchmarks for large language models" (#10)⁠

    OSainz +1: AmeyaPrabhu
    Verified signature
    f5daf9b

  1. Added Contamination Info on Old Models: GPT3, FLAN, GLaM, PaLM, PaLM 2 (#13)⁠

    OSainz +1: AmeyaPrabhu
    Verified signature
    c4acbf6

  2. Contamination results based on "Data Contamination Quiz" (#9)⁠

    OSainz +1: shahriargolchin
    Verified signature
    36aaa79

  3. Fix arxiv links

    OSainz
    7127ae8

  4. Code contamination in HumanEval and MBPP (#12)⁠

    OSainz +1: AmeyaPrabhu
    Verified signature
    ffb0d75

  1. Add model-based results for MedNLI, RadNLI for GPT-3.5 and GPT-4 (#8)⁠

    Iker +1: j-chim
    Verified signature
    d57b460

  2. Add data from "An Open-Source Data Contamination Report for Large Language Models" (#5)⁠

    Iker +1: vishaal27
    Verified signature
    619ed3b

  1. Import data from LM Contamination Index (#7)⁠

    Iker +2: borgr, OSainz
    Verified signature
    e1c863c

  1. Fix format issues

    OSainz
    9b28f49

  2. Add data from "Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus" (#6)⁠

    Iker +1: vishaal27
    Verified signature
    935e79b

  1. Add reports from Time Travel In LLMs paper (#3)⁠

    OSainz
    Verified signature
    5a41656

  2. Fix super_glue replace

    OSainz
    ab79de8

  3. Add PR links to previous commits

    OSainz
    f35c65c

  1. Add data from WIMBD paper (#2)⁠

    OSainz
    Verified signature
    eadd64a

  1. Small changes

    OSainz
    fd6f269

  1. Initital commit

    Iker
    eba8a37