2022.acl-long.516.pdf

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

• [2005.14165] Language Models are Few-Shot Learnersarxiv.org
• Self-Adapting Language Modelsarxiv.org
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• Position: It's Time to Optimize for Self-Consistencytime-for-consistency.github.io
• 2308.03958arxiv.org
• 2212.03827arxiv.org
• Prediction, Explanation, or Over-interpretation?elena-baixy.github.io
• Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
• Do we still need clinical language models?proceedings.mlr.press
• A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Modelsarxiv.org
• Language Models can Solve Computer Tasksarxiv.org
• [2601.10160] Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignmentarxiv.org