skip to main content

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • Home
  • Search Results
  • Page 1 of 4

Search for: All records

Creators/Authors contains: "Smith, Noah"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. ; ; ; ; ; ( , Conference on Language Modeling)
    Free, publicly-accessible full text available October 7, 2025
  2. ; ; ; ; ( , International Conference on Machine Learning (ICML) 2024)
    A major risk of using language models in practical applications is their tendency to hallucinate incorrect statements. Hallucinations are often attributed to knowledge gaps in LMs, but we hypothesize that in some cases, when justifying previously generated hallucinations, LMs output false claims that they can separately recognize as incorrect. We construct three question-answering datasets where ChatGPT and GPT-4 often state an incorrect answer and offer an explanation with at least one incorrect claim. Crucially, we find that ChatGPT and GPT-4 can identify 67% and 87% of their own mistakes, respectively. We refer to this phenomenon as hallucination snowballing: an LM over-commits to early mistakes, leading to more mistakes that it otherwise would not make. 
    more » « less
    Free, publicly-accessible full text available July 21, 2025
  3. ; ; ; ; ; ; ( , ICLR)
    Free, publicly-accessible full text available May 9, 2025
  4. ; ; ; ; ; ; ; ; ; ; et al ( , Neurips)
    Free, publicly-accessible full text available May 31, 2025
  5. ; ; ; ; ; ; ; ; ; ; et al ( , ICLR)
    Free, publicly-accessible full text available May 9, 2025
  6. ; ; ; ; ; ( , Findings of the Association for Computational Linguistics: EMNLP 2023)
    Full Text Available 
  7. ; ; ; ; ( , Proceedings of the The 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023))
    Model explanations that shed light on the model’s predictions are becoming a desired additional output of NLP models, alongside their predictions. Challenges in creating these explanations include making them trustworthy and faithful to the model’s predictions. In this work, we propose a novel framework for guiding model explanations by supervising them explicitly. To this end, our method, LEXPLAIN, uses task-related lexicons to directly supervise model explanations. This approach consistently improves the plausibility of model’s explanations without sacrificing performance on the task, as we demonstrate on sentiment analysis and toxicity detection. Our analyses show that our method also demotes spurious correlations (i.e., with respect to African American English dialect) on toxicity detection, improving fairness. 
    more » « less
    Full Text Available 
  8. ; ; ; ( , Findings of the Association for Computational Linguistics: EMNLP 2022)
    Full Text Available 
  9. ; ; ; ; ( , Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers))
    Full Text Available 
  10. ; ; ; ; ; ( , Association for Computational Linguistics)
    Full Text Available