Misconceptions
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 2
Measures whether a model can discern popular misconceptions from the truth.
Example:
input: The daddy longlegs spider is the most venomous spider in the world.
choice: T
choice: F
answer: F
input: Karl Benz is correctly credited with the invention of the first modern automobile.
choice: T
choice: F
answer: T
Source: BIG-bench
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/learn-co-students/dsc-3-28-12-graph-connectivity-community-detection-online-ds-pt-011419
https://github.com/learn-co-students/dsc-3-28-12-graph-connectivity-community-detection-online-ds-pt-100118
https://github.com/learn-co-students/dsc-3-28-12-graph-connectivity-community-detection-online-ds-pt-112618
https://github.com/learn-co-students/dsc-3-28-12-graph-connectivity-community-detection-online-ds-sp-000
https://github.com/learn-co-students/dsc-3-28-12-graph-connectivity-community-detection-staff
https://github.com/lightning-uq-box/lightning-uq-box
https://github.com/lurosenb/sass
https://github.com/niyunsheng/ems-sd
Factuality Enhanced Language Models for Open-Ended Text Generation
https://github.com/nkluge-correa/teenytinyllama
https://github.com/ranggihwang/pregated_moe
Factuality Enhanced Language Models for Open-Ended Text Generation
https://github.com/rst-tu-dortmund/lord
Parting with Misconceptions about Learning-based Vehicle Motion Planning
https://github.com/ruanchaves/eplm
On the Stability of Fine-tuning BERT: Misconceptions, Explanations, and Strong Baselines
https://github.com/rvlopes/gloria
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
https://github.com/tanny411/llm-reliability-and-consistency-evaluation
Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording
https://github.com/triton-inference-server/fastertransformer_backend
Factuality Enhanced Language Models for Open-Ended Text Generation
https://github.com/vrt1shjwlkr/ndss21-model-poisoning
https://github.com/wiseodd/laplace-bayesopt
https://github.com/yizhongw/truthfulqa_reeval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.