skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

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


Title: Can ChatGPT Understand Causal Language in Science Claims?
This study evaluated ChatGPT’s ability to understand causal language in science papers and news by testing its accuracy in a task of labeling the strength of a claim as causal, conditional causal, correlational, or no relationship. The results show that ChatGPT is still behind the existing fine-tuned BERT models by a large margin. ChatGPT also had difficulty understanding conditional causal claims mitigated by hedges. However, its weakness may be utilized to improve the clarity of human annotation guideline. Chain-of-thought prompting was faithful and helpful for improving prompt performance, but finding the optimal prompt is difficult with inconsistent results and the lack of effective method to establish cause-effect between prompts and outcomes, suggesting caution when generalizing prompt engineering results across tasks or models.  more » « less
Award ID(s):
1952353
PAR ID:
10552287
Author(s) / Creator(s):
; ; ;
Publisher / Repository:
Association for Computational Linguistics
Date Published:
Page Range / eLocation ID:
379 to 389
Format(s):
Medium: X
Location:
Toronto, Canada
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing)
    Instruction-tuned large language models (LLMs), such as ChatGPT, have led to promising zero-shot performance in discriminative natural language understanding (NLU) tasks. This involves querying the LLM using a prompt containing the question, and the candidate labels to choose from. The question-answering capabilities of ChatGPT arise from its pre-training on large amounts of human-written text, as well as its subsequent fine-tuning on human preferences, which motivates us to ask: Does ChatGPT also inherit humans’ cognitive biases? In this paper, we study the primacy effect of ChatGPT: the tendency of selecting the labels at earlier positions as the answer. We have two main findings: i) ChatGPT’s decision is sensitive to the order of labels in the prompt; ii) ChatGPT has a clearly higher chance to select the labels at earlier positions as the answer. We hope that our experiments and analyses provide additional insights into building more reliable ChatGPT-based solutions. We release the source code at https://github.com/wangywUST/PrimacyEffectGPT. 
    more » « less
  2. ; ; ; (, ACM)
    The ChatGPT4PCG competition calls for participants to submit inputs to ChatGPT or prompts that guide its output toward instructions to generate levels as sequences of Tetris-like block drops. Prompts submitted to the competition are queried by ChatGPT to generate levels that resemble letters of the English alphabet. Levels are evaluated based on their similarity to the target letter and physical stability in the game engine. This provides a quantitative evaluation setting for prompt-based procedural content generation (PCG), an approach that has been gaining popularity in PCG, as in other areas of generative AI. This paper focuses on replicating and generalizing the competition results. The replication experiments in the paper first aim to test whether the number of responses gathered from ChatGPT is sufficient to account for the stochasticity. We requery the original prompt submissions and rerun the original scripts from the competition, on different machines, about six months after the competition. We find that results largely replicate, except that two of the 15 submissions do much better in our replication, for reasons we can only partly determine. When it comes to generalization, we notice that the top-performing prompt has instructions for all 26 target levels hardcoded, which is at odds with the PCGML goal of generating new, previously unseen content from examples. We perform experiments in more restricted zero-shot and few-shot prompting scenarios, and find that generalization remains a challenge for current approaches. 
    more » « less
  3. ; ; ; (, Applied Soft Computing)
    The rise of e-commerce and social networking platforms has led to an increase in the disclosure of personal health information within user-generated content. This study investigates the application of large language models (LLMs) to detect and sanitize sensitive health data shared by users across platforms such as Amazon, patient.info, and Facebook. We propose a methodology that leverages LLMs to evaluate both the sensitivity of disclosed information and the platform-specific semantics of the content. Through prompt engineering, our method identifies sensitive information and rephrases it to minimize disclosure while preserving content similarity. ChatGPT serves as the LLM in this study due to its versatility. Empirical results suggest that ChatGPT can reliably assign sensitivity scores to user-generated text and generate sanitized versions that effectively preserve the original meaning. 
    more » « less
  4. ; (, PMLR)
    We consider the problem of identifying a conditional causal effect through covariate adjustment. We focus on the setting where the causal graph is known up to one of two types of graphs: a maximally oriented partially directed acyclic graph (MPDAG) or a partial ancestral graph (PAG). Both MPDAGs and PAGs represent equivalence classes of possible underlying causal models. After defining adjustment sets in this setting, we provide a necessary and sufficient graphical criterion – the conditional adjustment criterion – for finding these sets under conditioning on variables unaffected by treatment. We further provide explicit sets from the graph that satisfy the conditional adjustment criterion, and therefore, can be used as adjustment sets for conditional causal effect identification. 
    more » « less
  5. ; ; ; ; ; ; ; (, Machine Learning Research Press)
    Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-quality or buggy code, and more. Here, we explore alternative objectives for pretraining LMs in a way that also guides them to generate text aligned with human preferences. We benchmark five objectives for pretraining with human feedback across three tasks and study how they affect the trade-off between alignment and capabilities of pretrained LMs. We find a Pareto optimal and simple approach among those we explored: conditional training, or learning distribution over tokens conditional on their human preference scores given by a reward model. Conditional training reduces the rate of undesirable content by up to an order of magnitude, both when generating without a prompt and with an adversarially chosen prompt. Moreover, conditional training maintains the downstream task performance of standard LM pretraining, both before and after task-specific finetuning. Pretraining with human feedback results in much better preference satisfaction than standard LM pretraining followed by finetuning with feedback, i.e., learning and then unlearning undesirable behavior. Our results suggest that we should move beyond imitation learning when pretraining LMs and incorporate human preferences from the start of training. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email