2022.acl-long.516.pdf
aclanthology.org · 7,295 words · saved by 1 readers
N/A
The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Fail Samuel R. Bowman New York University bowman@nyu.edu Abstract Researchers in NLP often frame and discuss research results in ways that serve to deem- phasize the field’s successes, often in response to the field’s widespread hype. Though well- meaning, this has yielded many misleading or false claims about the…
related reading
- Current AIs seem pretty misaligned to me — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Why I Think More NLP Researchers Should Engage with AI Safety Concerns – NYU Alignment Research Groupwp.nyu.edu
- machine learning imindslice.substack.com
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
- Current AIs seem pretty misaligned to meblog.redwoodresearch.org
- Assessing skeptical views of interpretability research | Christopher Pottsweb.stanford.edu
- Is AI Reasoning Right for the Wrong Reasons? | Quanta Magazinequantamagazine.org
- Surfacing Pathological Behaviors in Language Models | Transluce AItransluce.org
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- When ChatGPT Broke an Entire Field: An Oral History | Quanta Magazinequantamagazine.org
- Explaining AI Alignment as an NLPer and Why I am Working on Itruiqizhong.substack.com