Kuiz berkaitan panduan · Keras Tahap
Kuiz BloombergGPT dan LLM Kewangan
Fahami persediaan penyelidikan BloombergGPT, bandingkan model kewangan dan umum, dan nilaikan output kewangan terhadap bukti sumber bertarikh.
soalan 1 daripada 8
Apakah laporan akhbar BloombergGPT tentang data pralatihannya?
Pratonton setiap soalan8 soalan
Jawapan dan penjelasan muncul semasa anda mengambil kuiz.
- Apakah laporan akhbar BloombergGPT tentang data pralatihannya?
- A mixture of financial and general-purpose text
- Only private analyst recommendations
- Only unlabeled stock-price time series
- A corpus consisting entirely of SEC filings
- Apakah skor yang kukuh pada satu penanda aras kewangan?
- The model is safe for every trading decision
- Performance on that benchmark under its test setup
- That every financial fact is current
- That a model will outperform on all languages
- Mengapa menilai pengekstrakan berangka secara berasingan daripada ringkasan fasih?
- Fluency guarantees arithmetic
- Numbers do not appear in financial documents
- A polished summary can still contain an incorrect figure or period
- Numerical tests cannot use source documents
- Bagaimanakah pemfailan yang diperoleh semula harus digunakan dalam aliran kerja LLM kewangan?
- Assume the model will calculate every figure correctly
- Remove the filing date to simplify the prompt
- Treat a citation as investment advice
- Verify claims and calculations against the dated filing
- Set penilaian manakah yang berguna apabila membandingkan model umum dan pengkhususan kewangan?
- The same representative held-out examples for both models
- Different questions chosen to favor each model
- Only prompts used during training
- A set containing only easy positive cases
- Why check a financial model for temporal leakage?
- To make its output more persuasive
- Future information in a test example can make results look unrealistically strong
- To remove all source documents
- It is required to increase model size
- What should a model do when asked about a figure in a filing?
- Invent a likely number when retrieval fails
- Hide the currency and period
- Preserve units and reporting period and support the figure with the source
- Use a recent figure from another company
- How should teams use BloombergGPT’s published benchmark findings?
- As a guarantee for every financial task
- As proof proprietary data always improve models
- As a replacement for their own validation
- As evidence limited to the benchmarks and methods reported