An official website of the United States government
Many selection procedures involve ordering candidates according to their qualifications. For example, a university might order applicants according to a perceived probability of graduation within four years, and then select the top 1000 applicants. In this work, we address the problem of ranking members of a population according to their “probability” of success, based on a training set of historical binary outcome data (e.g., graduated in four years or not). We show how to obtain rankings that satisfy a number of desirable accuracy and fairness criteria, despite the coarseness of the training data. As the task of ranking is global (the rank of every individual depends not only on their own qualifications, but also on every other individuals’ qualifications), ranking is more subtle and vulnerable to manipulation than standard prediction tasks. Towards mitigating unfair discrimination caused by inaccuracies in rankings, we develop two parallel definitions of evidence-based rankings. The first definition relies on a semantic notion of domination-compatibility: if the training data suggest that members of a set S are more qualified (on average) than the members of T, then a ranking that favors T over S (where T dominates S) is blatantly inconsistent with the evidence, and likely to be discriminatory. The definition asks for domination-compatibility, not just for a pair of sets, but rather for every pair of sets from a rich collection C of subpopulations. The second definition aims at precluding even more general forms of discrimination; this notion of evidence-consistency requires that the ranking must be justified on the basis of consistency with the expectations for every set in the collection C. Somewhat surprisingly, while evidence-consistency is a strictly stronger notion than domination-compatibility when the collection C is predefined, the two notions are equivalent when the collection C may depend on the ranking in question.
more »
« less
Coverage-based Example Selection for In-Context Learning
In-context learning (ICL), the ability of large language models to perform novel tasks by conditioning on a prompt with a few task examples, requires these examples to be informative about the test instance. The standard approach of independently ranking and selecting the most similar examples selects redundant examples while omitting important information. In this work, we show that BERTScore-Recall (BSR) selects better examples that demonstrate more of the salient aspects, e.g. reasoning patterns, of the test input. We further extend BSR and many standard metrics to easily optimizable set-level metrics, giving still better coverage of those salient aspects. On 15 datasets spanning 6 tasks and with 7 diverse LLMs, we show that (1) BSR is the superior metric for in-context example selection across the board, and (2) for compositional tasks, set selection using Set-BSR outperforms independent ranking by up to 17 points on average and, despite being training-free, surpasses methods that leverage task or LLM-specific training.
more »
« less
- Award ID(s):
- 2046873
- PAR ID:
- 10526343
- Publisher / Repository:
- Association for Computational Linguistics
- Date Published:
- Page Range / eLocation ID:
- 13924 to 13950
- Format(s):
- Medium: X
- Location:
- Singapore
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasksnull (Ed.)We study the transfer learning process between two linear regression problems. An important and timely special case is when the regressors are overparameterized and perfectly interpolate their training data. We examine a parameter transfer mechanism whereby a subset of the parameters of the target task solution are constrained to the values learned for a related source task. We analytically characterize the generalization error of the target task in terms of the salient factors in the transfer learning architecture, i.e., the number of examples available, the number of (free) parameters in each of the tasks, the number of parameters transferred from the source to target task, and the correlation between the two tasks. Our non-asymptotic analysis shows that the generalization error of the target task follows a two-dimensional double descent trend (with respect to the number of free parameters in each of the tasks) that is controlled by the transfer learning factors. Our analysis points to specific cases where the transfer of parameters is beneficial. Specifically, we show that transferring a specific set of parameters that generalizes well on the respective part of the source task can soften the demand on the task correlation level that is required for successful transfer learning. Moreover, we show that the usefulness of a transfer learning setting is fragile and depends on a delicate interplay among the set of transferred parameters, the relation between the tasks, and the true solution.more » « less
-
Meta-learning methods typically learn tasks under the assumption that all tasks are equally important. However, this assumption is often not valid. In real-world applications, tasks can vary both in their importance during different train- ing stages and in whether they contain noisy labeled data or not, making a uniform approach suboptimal. To address these issues, we propose the Data-Efficient and Robust Task Selection (DERTS) algorithm, which can be incorporated into both gradient and metric-based meta-learning algo- rithms. DERTS selects weighted subsets of tasks from task pools by minimizing the approximation error of the full gra- dient of task pools in the meta-training stage. The selected tasks are efficient for rapid training and robust towards noisy label scenarios. Unlike existing algorithms, DERTS does not require any architecture modification for training and can handle noisy label data in both the support and query sets. Analysis of DERTS shows that the algorithm follows similar training dynamics as learning on the full task pools. Experiments show that DERTS outperforms existing sam- pling strategies for meta-learning on both gradient-based and metric-based meta-learning algorithms in limited data budget and noisy task settings.more » « less
-
Ganguly, Debasis; Gangopadhyay, Surupendu; Mitra, Mandar; Majumder, Prasenjit (Ed.)For most queries, the set of relevant documents spans multiple subtopics. Inspired by the neural ranking models and query-specific neural clustering models, we develop Topic-Mono-BERT which performs both tasks jointly. Based on text embeddings of BERT, our model learns a shared embedding that is optimized for both tasks. The clustering hypothesis would suggest that embeddings which place topically similar text in close proximity will also perform better on ranking tasks. Our model is trained with the Wikimarks approach to obtain training signals for relevance and subtopics on the same queries. Our task is to identify overview passages that can be used to construct a succinct answer to the query. Our empirical evaluation on two publicly available passage retrieval datasets suggests that including the clustering supervision in the ranking model leads to about 16% improvement in identifying text passages that summarize different subtopics within a query.more » « less
-
Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT. As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of generating IGT. We explore whether LLMs can be effective at the task of interlinear glossing with in-context learning, without any traditional training. We propose new approaches for selecting examples to provide in-context, observing that targeted selection can significantly improve performance. We find that LLM-based methods beat standard transformer baselines, despite requiring no training at all. These approaches still underperform state-of-the-art supervised systems for the task, but are highly practical for researchers outside of the NLP community, requiring minimal effort to use.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.18653/v1/2023.findings-emnlp.930
