Having been trained on massive pretraining data, large language models have shown excellent performance on many knowledge-intensive tasks. However, pretraining data tends to contain misleading and even conflicting information, and it is intriguing to understand how LLMs handle these noisy data during training. In this study, we systematically analyze LLMs’ learning preferences for data with conflicting knowledge. We find that pretrained LLMs establish learning preferences similar to humans, i.e., preferences towards formal texts and texts with fewer spelling errors, resulting in faster learning and more favorable treatment of knowledge in data with such features when facing conflicts. This finding is generalizable across models and languages and is more evident in larger models. An in-depth analysis reveals that LLMs tend to trust data with features that signify consistency with the majority of data, and it is possible to instill new preferences and erase old ones by manipulating the degree of consistency with the majority data.

Large language models demonstrate reasonable multilingual abilities, despite predominantly English-centric pretraining. However, the spontaneous multilingual alignment in these models is shown to be weak, leading to unsatisfactory cross-lingual transfer and knowledge sharing. Previous works attempt to address this issue by explicitly injecting multilingual alignment information during or after pretraining. Thus for the early stage in pretraining, the alignment is weak for sharing information or knowledge across languages. In this paper, we propose PreAlign, a framework that establishes multilingual alignment prior to language model pretraining. PreAlign injects multilingual alignment by initializing the model to generate similar representations of aligned words and preserves this alignment using a code-switching strategy during pretraining. Extensive experiments in a synthetic English to English-Clone setting demonstrate that PreAlign significantly outperforms standard multilingual joint training in language modeling, zero-shot cross-lingual transfer, and cross-lingual knowledge application. Further experiments in real-world scenarios further validate PreAlign’s effectiveness across various model sizes.

Large-scale pretrained language models (LLMs), such as ChatGPT and GPT4, have shown strong abilities in multilingual translation, without being explicitly trained on parallel corpora. It is intriguing how the LLMs obtain their ability to carry out translation instructions for different languages. In this paper, we present a detailed analysis by finetuning a multilingual pretrained language model, XGLM-7.5B, to perform multilingual translation following given instructions. Firstly, we show that multilingual LLMs have stronger translation abilities than previously demonstrated. For a certain language, the translation performance depends on its similarity to English and the amount of data used in the pretraining phase. Secondly, we find that LLMs’ ability to carry out translation instructions relies on the understanding of translation instructions and the alignment among different languages. With multilingual finetuning with translation instructions, LLMs could learn to perform the translation task well even for those language pairs unseen during the instruction tuning phase.

Large Language Models (LLM) have demonstrated their strong ability in the field of machine translation, yet they suffer from high computational cost and latency. Therefore, transferring translation knowledge from giant LLMs to medium-sized machine translation models is a promising research direction. However, traditional knowledge distillation methods ignore the capability of student and teacher models, therefore repeatedly teaching student models on the knowledge they have learned, and failing to extend to novel contexts and knowledge. In this paper, we propose a framework called MT-Patcher, which transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner. Considering the current translation ability of student MT models, we only identify and correct their translation errors, instead of distilling the whole translation from the teacher. Leveraging the strong language abilities of LLMs, we instruct LLM teachers to synthesize diverse contexts and anticipate more potential errors for the student. Experiment results on translating both specific language phenomena and general MT benchmarks demonstrate that finetuning the MT model on about 10% examples can achieve comparable results to the traditional knowledge distillation method, and synthesized potential errors and diverse contexts further improve MT performances on unseen contexts and words.

This paper presents an analysis of the pre-trained Transformer model Neural Machine Translation (NMT) for the Ancient-Chinese-to-Modern-Chinese machine translation task.

Automatic word segmentation and part-of-speech tagging of ancient books can help relevant researchers to study ancient texts. In recent years, pre-trained language models have achieved significant improvements on text processing tasks. SikuRoberta is a pre-trained language model specially designed for automatic analysis of ancient Chinese texts. Although SikuRoberta significantly boosts performance on WSG and POS tasks on ancient Chinese texts, the lack of labeled data still limits the performance of the model. In this paper, to alleviate the problem of insufficient training data, We define hybrid tags to integrate WSG and POS tasks and design Roberta-CRF model to predict tags for each Chinese characters. Moreover, We generate synthetic labeled data based on the LSTM language model. To further mine knowledge in SikuRoberta, we generate the synthetic unlabeled data based on the Masked LM. Experiments show that the performance of the model is improved with the synthetic data, indicating that the effectiveness of the data augmentation methods.

Subword segmentation algorithms have been a de facto choice when building neural machine translation systems. However, most of them need to learn a segmentation model based on some heuristics, which may produce sub-optimal segmentation. This can be problematic in some scenarios when the target language has rich morphological changes or there is not enough data for learning compact composition rules. Translating at fully character level has the potential to alleviate the issue, but empirical performances of character-based models has not been fully explored. In this paper, we present an in-depth comparison between character-based and subword-based NMT systems under three settings: translating to typologically diverse languages, training with low resource, and adapting to unseen domains. Experiment results show strong competitiveness of character-based models. Further analyses show that compared to subword-based models, character-based models are better at handling morphological phenomena, generating rare and unknown words, and more suitable for transferring to unseen domains.

Definition generation, which aims to automatically generate dictionary definitions for words, has recently been proposed to assist the construction of dictionaries and help people understand unfamiliar texts. However, previous works hardly consider explicitly modeling the “components” of definitions, leading to under-specific generation results. In this paper, we propose ESD, namely Explicit Semantic Decomposition for definition Generation, which explicitly decomposes the meaning of words into semantic components, and models them with discrete latent variables for definition generation. Experimental results show that achieves top results on WordNet and Oxford benchmarks, outperforming strong previous baselines.