Work on instruction-tuned Large Language Models (LLMs) has used automatic methods based on text overlap and LLM judgments as cost-effective alternatives to human evaluation. In this paper, we perform a meta-evaluation of such methods and assess their reliability across a broad range of tasks. In evaluating how well automatic methods align with human evaluations, correlation metrics are the most commonly employed method despite their inherent limitations when dealing with ties and different scales. To address these shortcomings, we use Pairwise Accuracy as an alternative to standard correlation measures. We observe that while automatic evaluation methods can approximate human ratings under specific conditions, their validity is highly context-dependent. Specifically, the simple ROUGE-L metric correlates very well with human ratings for short-answer English tasks but is unreliable in free-form generation tasks and cross-lingual scenarios. The effectiveness of the more advanced method of using GPT-4 as a judge diminishes significantly if reference answers are not included in the prompt, which is the scenario where this method has the potential to provide the most value compared to other metrics. Our findings enhance the understanding of how automatic methods should be applied and interpreted when developing and evaluating instruction-tuned LLMs.

Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low. Retrieval-augmented models commonly rely on a semantic retrieval mechanism based on the similarity between dense representations of the query chunk and potential neighbors. In this paper, we study the state-of-the-art Retro model and observe that its performance gain is better explained by surface-level similarities, such as token overlap. Inspired by this, we replace the semantic retrieval in Retro with a surface-level method based on BM25, obtaining a significant reduction in perplexity. As full BM25 retrieval can be computationally costly for large datasets, we also apply it in a re-ranking scenario, gaining part of the perplexity reduction with minimal computational overhead.

Recent work on the Retrieval-Enhanced Transformer (RETRO) model has shown impressive results: off-loading memory from trainable weights to a retrieval database can significantly improve language modeling and match the performance of non-retrieval models that are an order of magnitude larger in size. It has been suggested that at least some of this performance gain is due to non-trivial generalization based on both model weights and retrieval. In this paper, we try to better understand the relative contributions of these two components. We find that the performance gains from retrieval to a very large extent originate from overlapping tokens between the database and the test data, suggesting less of non-trivial generalization than previously assumed. More generally, our results point to the challenges of evaluating the generalization of retrieval-augmented language models such as RETRO, as even limited token overlap may significantly decrease test-time loss. We release our code and model at https://github.com/TobiasNorlund/retro

In recent years, instruction finetuning models have received increased attention due to their remarkable zero-shot and generalization capabilities. However, the widespread implementation of these models has been limited to the English language, largely due to the costs and challenges associated with creating instruction datasets. To overcome this, automatic instruction generation has been proposed as a resourceful alternative. We see this as an opportunity for the adoption of instruction finetuning for other languages. In this paper we explore the viability of instruction finetuning for Swedish. We translate a dataset of generated instructions from English to Swedish, using it to finetune both Swedish and non-Swedish models. Results indicate that the use of translated instructions significantly improves the models’ zero-shot performance, even on unseen data, while staying competitive with strong baselines ten times in size. We see this paper is a first step and a proof of concept that instruction finetuning for Swedish is within reach, through resourceful means, and that there exist several directions for further improvements.

Transformer-based models trained on text and vision modalities try to improve the performance on multimodal downstream tasks or tackle the problem Transformer-based models trained on text and vision modalities try to improve the performance on multimodal downstream tasks or tackle the problem of lack of grounding, e.g., addressing issues like models’ insufficient commonsense knowledge. While it is more straightforward to evaluate the effects of such models on multimodal tasks, such as visual question answering or image captioning, it is not as well-understood how these tasks affect the model itself, and its internal linguistic representations. In this work, we experiment with language models grounded in videos and measure the models’ performance on predicting masked words chosen based on their imageability. The results show that the smaller model benefits from video grounding in predicting highly imageable words, while the results for the larger model seem harder to interpret.of lack of grounding, e.g., addressing issues like models’ insufficient commonsense knowledge. While it is more straightforward to evaluate the effects of such models on multimodal tasks, such as visual question answering or image captioning, it is not as well-understood how these tasks affect the model itself, and its internal linguistic representations. In this work, we experiment with language models grounded in videos and measure the models’ performance on predicting masked words chosen based on their imageability. The results show that the smaller model benefits from video grounding in predicting highly imageable words, while the results for the larger model seem harder to interpret.

Words are properly segmented in the Persian writing system; in practice, however, these writing rules are often neglected, resulting in single words being written disjointedly and multiple words written without any white spaces between them. This paper addresses the problems of word segmentation and zero-width non-joiner (ZWNJ) recognition in Persian, which we approach jointly as a sequence labeling problem. We achieved a macro-averaged F1-score of 92.40% on a carefully collected corpus of 500 sentences with a high level of difficulty.

Ezafe is a grammatical particle in some Iranian languages that links two words together. Regardless of the important information it conveys, it is almost always not indicated in Persian script, resulting in mistakes in reading complex sentences and errors in natural language processing tasks. In this paper, we experiment with different machine learning methods to achieve state-of-the-art results in the task of ezafe recognition. Transformer-based methods, BERT and XLMRoBERTa, achieve the best results, the latter achieving 2.68% F1-score more than the previous state-of-the-art. We, moreover, use ezafe information to improve Persian part-of-speech tagging results and show that such information will not be useful to transformer-based methods and explain why that might be the case.

This paper presents the models submitted by Ghmerti team for subtasks A and B of the OffensEval shared task at SemEval 2019. OffensEval addresses the problem of identifying and categorizing offensive language in social media in three subtasks; whether or not a content is offensive (subtask A), whether it is targeted (subtask B) towards an individual, a group, or other entities (subtask C). The proposed approach includes character-level Convolutional Neural Network, word-level Recurrent Neural Network, and some preprocessing. The performance achieved by the proposed model is 77.93% macro-averaged F1-score.

Identification of the languages written using cuneiform symbols is a difficult task due to the lack of resources and the problem of tokenization. The Cuneiform Language Identification task in VarDial 2019 addresses the problem of identifying seven languages and dialects written in cuneiform; Sumerian and six dialects of Akkadian language: Old Babylonian, Middle Babylonian Peripheral, Standard Babylonian, Neo-Babylonian, Late Babylonian, and Neo-Assyrian. This paper describes the approaches taken by SharifCL team to this problem in VarDial 2019. The best result belongs to an ensemble of Support Vector Machines and a naive Bayes classifier, both working on character-level features, with macro-averaged F1-score of 72.10%.