While the Large Language Models (LLMs) dominate a majority of language understanding tasks, previous work shows that some of these results are supported by modelling spurious correlations of training datasets. Authors commonly assess model robustness by evaluating their models on out-of-distribution (OOD) datasets of the same task, but these datasets might share the bias of the training dataset. We propose a simple method for measuring a scale of models’ reliance on any identified spurious feature and assess the robustness towards a large set of known and newly found prediction biases for various pre-trained models and debiasing methods in Question Answering (QA). We find that the reported OOD gains of debiasing methods can not be explained by mitigated reliance on biased features, suggesting that biases are shared among different QA datasets. We further evidence this by measuring that performance of OOD models depends on bias features comparably to the ID model. Our findings motivate future work to refine the reports of LLMs’ robustness to a level of known spurious features.

Despite outstanding performance in many tasks, language models are notoriously inclined to make factual errors in tasks requiring arithmetic computation. We address this deficiency by creating Calc-X, a collection of datasets that demonstrates the appropriate use of a calculator in reasoning chains. Calc-X is suitable for teaching language models to offload computations to a symbolic system. We survey and unify several existing chain-of-thought datasets into a proposed format, resulting in a standard collection of over 300,000 samples requiring arithmetic reasoning. Finally, we use the new Calc-X collection to train open-source calculator-using models and show that these models approximately double the accuracy of generating correct results compared to vanilla language model baselines.

Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model’s ability to generalize to other domains, making the open-ended deployments of the adapted models prone to errors. This work introduces novel training objectives built upon a semantic similarity of the predicted tokens to the reference. Our results show that (1) avoiding the common assumption of a single correct prediction by constructing the training target from tokens’ semantic similarity can largely mitigate catastrophic forgetting of adaptation, while (2) preserving the adaptation in-domain quality, (3) with negligible additions to compute costs. In the broader context, the objectives grounded in a continuous token similarity pioneer the exploration of the middle ground between the efficient but naive exact-match token-level objectives and expressive but computationally- and resource-intensive sequential objectives.

Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the ability to interact with users of languages outside English presents a great potential for broadening the applicability of language technologies to non-English speakers. In this work, we collect the infrastructure necessary for training and evaluation of ICL in a selection of Slavic languages: Czech, Polish, and Russian. We link a diverse set of datasets and cast these into a unified instructional format through a set of transformations and newly-crafted templates written purely in target languages. Using the newly-curated dataset, we evaluate a set of the most recent in-context learners and compare their results to the supervised baselines. Finally, we train, evaluate and publish a set of in-context learning models that we train on the collected resources and compare their performance to previous work. We find that ICL models tuned in English are also able to learn some tasks from non-English contexts, but multilingual instruction fine-tuning consistently improves the ICL ability. We also find that the massive multitask training can be outperformed by single-task training in the target language, uncovering the potential for specializing in-context learners to the language(s) of their application.

Large language models show an emergent ability to learn a new task from a small number of input-output demonstrations. However, recent work shows that in-context learners largely rely on their pre-trained knowledge, such as the sentiment of the labels, instead of finding new associations in the input. However, the commonly-used few-shot evaluation settings using a random selection of in-context demonstrations can not disentangle models’ ability to learn a new skill from demonstrations, as most of the randomly-selected demonstrations do not present relations informative for prediction beyond exposing the new task distribution. To disentangle models’ in-context learning ability independent of models’ memory, we introduce a Conceptual few-shot learning method selecting the demonstrations sharing a possibly-informative concept with the predicted sample. We extract a set of such concepts from annotated explanations and measure how much can models benefit from presenting these concepts in few-shot demonstrations. We find that smaller models are more sensitive to the presented concepts. While some of the models are able to benefit from concept-presenting demonstrations for each assessed concept, we find that none of the assessed in-context learners can benefit from all presented reasoning concepts consistently, leaving the in-context concept learning an open challenge.

Although pre-trained named entity recognition (NER) models are highly accurate on modern corpora, they underperform on historical texts due to differences in language OCR errors. In this work, we develop a new NER corpus of 3.6M sentences from late medieval charters written mainly in Czech, Latin, and German.We show that we can start with a list of known historical figures and locations and an unannotated corpus of historical texts, and use information retrieval techniques to automatically bootstrap a NER-annotated corpus. Using our corpus, we train a NER model that achieves entity-level Precision of 72.81–93.98% with 58.14–81.77% Recall on a manually-annotated test dataset. Furthermore, we show that using a weighted loss function helps to combat class imbalance in token classification tasks. To make it easy for others to reproduce and build upon our work, we publicly release our corpus, models, and experimental code.

This paper introduces Adaptor library, which transposes traditional model-centric approach composed of pre-training + fine-tuning steps to objective-centric approach, composing the training process by applications of selected objectives. We survey research directions that can benefit from enhanced objective-centric experimentation in multitask training, custom objectives development, dynamic training curricula, or domain adaptation. Adaptor aims to ease reproducibility of these research directions in practice. Finally, we demonstrate the practical applicability of Adaptor in selected unsupervised domain adaptation scenarios.

Despite their outstanding performance, large language models (LLMs) suffer notorious flaws related to their preference for shallow textual relations over full semantic complexity of the problem. This proposal investigates a common denominator of this problem in their weak ability to generalise outside of the training domain. We survey diverse research directions providing estimations of model generalisation ability and find that incorporating some of these measures in the training objectives leads to enhanced distributional robustness of neural models. Based on these findings, we present future research directions enhancing the robustness of LLMs.

Unsupervised representation learning of words from large multilingual corpora is useful for downstream tasks such as word sense disambiguation, semantic text similarity, and information retrieval. The representation precision of log-bilinear fastText models is mostly due to their use of subword information. In previous work, the optimization of fastText’s subword sizes has not been fully explored, and non-English fastText models were trained using subword sizes optimized for English and German word analogy tasks. In our work, we find the optimal subword sizes on the English, German, Czech, Italian, Spanish, French, Hindi, Turkish, and Russian word analogy tasks. We then propose a simple n-gram coverage model and we show that it predicts better-than-default subword sizes on the Spanish, French, Hindi, Turkish, and Russian word analogy tasks. We show that the optimization of fastText’s subword sizes matters and results in a 14% improvement on the Czech word analogy task. We also show that expensive parameter optimization can be replaced by a simple n-gram coverage model that consistently improves the accuracy of fastText models on the word analogy tasks by up to 3% compared to the default subword sizes, and that it is within 1% accuracy of the optimal subword sizes.

This work introduces a simple regressive ensemble for evaluating machine translation quality based on a set of novel and established metrics. We evaluate the ensemble using a correlation to expert-based MQM scores of the WMT 2021 Metrics workshop. In both monolingual and zero-shot cross-lingual settings, we show a significant performance improvement over single metrics. In the cross-lingual settings, we also demonstrate that an ensemble approach is well-applicable to unseen languages. Furthermore, we identify a strong reference-free baseline that consistently outperforms the commonly-used BLEU and METEOR measures and significantly improves our ensemble’s performance.