An official website of the United States government
The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We conduct a "behavorial" study of LLMs to benchmark their capability in generating causal arguments. Across a wide range of tasks, we find that LLMs can generate text corresponding to correct causal arguments with high probability, surpassing the best-performing existing methods. Algorithms based on GPT-3.5 and 4 outperform existing algorithms on a pairwise causal discovery task (97%, 13 points gain), counterfactual reasoning task (92%, 20 points gain) and event causality (86% accuracy in determining necessary and sufficient causes in vignettes). We perform robustness checks across tasks and show that the capabilities cannot be explained by dataset memorization alone, especially since LLMs generalize to novel datasets that were created after the training cutoff date. That said, LLMs exhibit unpredictable failure modes, and we discuss the kinds of errors that may be improved and what are the fundamental limits of LLM-based answers. Overall, by operating on the text metadata, LLMs bring capabilities so far understood to be restricted to humans, such as using collected knowledge to generate causal graphs or identifying background causal context from natural language. As a result, LLMs may be used by human domain experts to save effort in setting up a causal analysis, one of the biggest impediments to the widespread adoption of causal methods. Given that LLMs ignore the actual data, our results also point to a fruitful research direction of developing algorithms that combine LLMs with existing causal techniques. Code and datasets are available at https://github.com/py-why/pywhy-llm.
more »
« less
A Study of Extracting Causal Relationships from Text
Discovering causal knowledge is an important aspect of much scientific research and such findings are often recorded in scholarly articles. Automatically identifying such knowledge from article text can be a useful tool and can act as an impetus for further research on those topics. Numerous applications, including building a causal knowledge graph, making pipelines for root cause analysis, discovering opportunities for drug discovery, and overall, a scalable building block towards turning large pieces of text into organized information can be built following such an approach. However, it requires robust methods to identify and aggregate causal knowledge from a large set of articles. The main challenge in designing new methods is the absence of a large labeled dataset. As a result, existing methods trained on existing datasets with limited size and variations in linguistic pattern, are unable to generalize well on unseen text. In this paper, we explore multiple unsupervised approaches, including a reinforcement learning-based model that learns to identify causal sentences from a small set of labeled sentences. We describe and discuss in detail our experiments for each approach to further encourage exploration of methods that can be re-utilized for different tasks as well, as opposed to simply exploring a supervised learning process which although superior in performance lacks the versatility to be re-purposed for slightly different tasks. We evaluate our methods on a custom-created dataset and show unique techniques to extract cause-effect relationships from the English language.
more »
« less
- Award ID(s):
- 1948322
- PAR ID:
- 10448536
- Editor(s):
- Arai, Kohei
- Date Published:
- Journal Name:
- Intelligent Systems and Applications. IntelliSys 2022. Lecture Notes in Networks and Systems, vol 544. Springer, Cham.
- Volume:
- 544
- Page Range / eLocation ID:
- 807-828
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Knowing whether a published research result can be replicated is important. Carrying out direct replication of published research incurs a high cost. There are efforts tried to use machine learning aided methods to predict scientific claims’ replicability. However, existing machine learning aided approaches use only hand-extracted statistics features such as p-value, sample size, etc. without utilizing research papers’ text information and train only on a very small size of annotated data without making the most use of a large number of unlabeled articles. Therefore, it is desirable to develop effective machine learning aided automatic methods which can automatically extract text information as features so that we can benefit from Natural Language Processing techniques. Besides, we aim for an approach that benefits from both labeled and the large number of unlabeled data. In this paper, we propose two weakly supervised learning approaches that use automatically extracted text information of research papers to improve the prediction accuracy of research replication using both labeled and unlabeled datasets. Our experiments over real-world datasets show that our approaches obtain much better prediction performance compared to the supervised models utilizing only statistic features and a small size of labeled dataset. Further, we are able to achieve an accuracy of 75.76% for predicting the replicability of research.more » « less
-
null (Ed.)Scientific literature, as one of the major knowledge resources, provides abundant textual evidence that has great potential to support high-quality scientific hypothesis validation. In this paper, we study the problem of textual evidence mining in scientific literature: given a scientific hypothesis as a query triplet, find the textual evidence sentences in scientific literature that support the input query. A critical challenge for textual evidence mining in scientific literature is to retrieve high-quality textual evidence without human supervision. Because it is non-trivial to obtain a large set of human-annotated articles con-taining evidence sentences in scientific literature. To tackle this challenge, we propose EVIDENCEMINER, a high-quality textual evidence retrieval method for scientific literature without human-annotated training examples. To achieve high-quality textual evidence retrieval, we leverage heterogeneous information from both existing knowledge bases and massive unstructured text. We propose to construct a large heterogeneous information network (HIN) to build connections between the user-input queries and the candidate evidence sentences. Based on the constructed HIN, we propose a novel HIN embedding method that directly embeds the nodes onto a spherical space to improve the retrieval performance. Quantitative experiments on a huge biomedical literature corpus (over 4 million sentences) demonstrate that EVIDENCEMINER significantly outperforms baseline methods for unsupervised textual evidence retrieval. Case studies also demonstrate that our HIN construction and embedding greatly benefit many downstream applications such as textual evidence interpretation and synonym meta-pattern discovery.more » « less
-
null (Ed.)Recent years have witnessed the enormous success of text representation learning in a wide range of text mining tasks. Earlier word embedding learning approaches represent words as fixed low-dimensional vectors to capture their semantics. The word embeddings so learned are used as the input features of task-specific models. Recently, pre-trained language models (PLMs), which learn universal language representations via pre-training Transformer-based neural models on large-scale text corpora, have revolutionized the natural language processing (NLP) field. Such pre-trained representations encode generic linguistic features that can be transferred to almost any text-related applications. PLMs outperform previous task-specific models in many applications as they only need to be fine-tuned on the target corpus instead of being trained from scratch. In this tutorial, we introduce recent advances in pre-trained text embeddings and language models, as well as their applications to a wide range of text mining tasks. Specifically, we first overview a set of recently developed self-supervised and weakly-supervised text embedding methods and pre-trained language models that serve as the fundamentals for downstream tasks. We then present several new methods based on pre-trained text embeddings and language models for various text mining applications such as topic discovery and text classification. We focus on methods that are weakly-supervised, domain-independent, language-agnostic, effective and scalable for mining and discovering structured knowledge from large-scale text corpora. Finally, we demonstrate with real world datasets how pre-trained text representations help mitigate the human annotation burden and facilitate automatic, accurate and efficient text analyses.more » « less
-
In this paper, we investigate the problem of discovering both direct and indirect discrimination from the historical data, and removing the discriminatory effects before the data is used for predictive analysis (e.g., building classifiers). The main drawback of existing methods is that they cannot distinguish the part of influence that is really caused by discrimination from all correlated influences. In our approach, we make use of the causal network to capture the causal structure of the data. Then we model direct and indirect discrimination as the path-specific effects, which accurately identify the two types of discrimination as the causal effects transmitted along different paths in the network. Based on that, we propose an effective algorithm for discovering direct and indirect discrimination, as well as an algorithm for precisely removing both types of discrimination while retaining good data utility. Experiments using the real dataset show the effectiveness of our approaches.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-031-16075-2_59
