Python 中的 LLM 入门
Jasmin Ludolf
Senior Data Science Content Developer, DataCamp
多语言支持: 语言多样性、资源可用性、适应性

开放 vs 封闭 LLM 的两难: 协作 vs 负责任使用

模型可扩展性: 表达能力、计算需求、训练要求

偏见: 偏倚训练数据,不公平的语言理解与生成


降低 LLM 幻觉的策略:

aggregation="maximum" 返回所有输入中的最大毒性分数 aggregation="ratio" 返回毒性>0.5的预测占比(%)toxicity_metric = load("toxicity") texts_1 = ["Everyone in the team adores him", "He is a true genius, pure talent"] texts_2 = ["Nobody in the team likes him", "He is a useless 'good-for-nothing'"]toxicity_results_1 = toxicity_metric.compute(predictions=texts_1,aggregation="maximum") toxicity_results_2 = toxicity_metric.compute(predictions=texts_2, aggregation="maximum") print("Toxicity Sentences 1:", toxicity_results_1) print("Toxicity Sentences 2:", toxicity_results_2)
Toxicity Sentences 1: {'max_toxicity': 0.0001386617950629443}
Toxicity Sentences 2: {'max_toxicity': 0.012273495085537434}
Regard: 语言极性与对特定人群的偏见感知
分别评估与两组相关的 LLM 输出 的 regard 分数
regard = load("regard") group1 = ['abc are described as loyal employees', 'abc are ambitious in their career expectations'] group2 = ['abc are known for causing lots of team conflicts', 'abc are verbally violent']polarity_results_1 = regard.compute(data=group1) polarity_results_2 = regard.compute(data=group2)
for result in polarity_results_1['regard']:
print(result)
[{'label': 'positive', 'score': 0.9098386764526367},
{'label': 'neutral', 'score': 0.059396952390670776},
{'label': 'other', 'score': 0.026468101888895035},
{'label': 'negative', 'score': 0.004296252969652414}]
[{'label': 'positive', 'score': 0.7809812426567078},
{'label': 'neutral', 'score': 0.18085983395576477},
{'label': 'other', 'score': 0.030492952093482018},
{'label': 'negative', 'score': 0.007666013203561306}]
for result in polarity_results_2['regard']:
print(result)
[{'label': 'negative', 'score': 0.9658734202384949},
{'label': 'other', 'score': 0.021555885672569275},
{'label': 'neutral', 'score': 0.012026479467749596},
{'label': 'positive', 'score': 0.0005441228277049959}]
[{'label': 'negative', 'score': 0.9774736166000366},
{'label': 'other', 'score': 0.012994581833481789},
{'label': 'neutral', 'score': 0.008945506066083908},
{'label': 'positive', 'score': 0.0005862844991497695}]
Python 中的 LLM 入门