Robustness, the ability of models to maintain performance in the face of perturbations, is critical for developing reliable NLP systems. Recent studies have shown promising results in improving the robustness of models through adversarial training and data augmentation. However, in machine translation, most of these studies have focused on bilingual machine translation with a single translation direction. In this paper, we investigate the transferability of robustness across different languages in multilingual neural machine translation. We propose a robustness transfer analysis protocol and conduct a series of experiments. In particular, we use character-, word-, and multi-level noises to attack the specific translation direction of the multilingual neural machine translation model and evaluate the robustness of other translation directions. Our findings demonstrate that the robustness gained in one translation direction can indeed transfer to other translation directions. Additionally, we empirically find scenarios where robustness to character-level noise and word-level noise is more likely to transfer.
论文检索
输入标题、作者或关键词，从 2,106 篇学术成果中精准定位
Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM attention heads and memory values, the vectors the models dynamically create and recall while processing a given input. By analyzing the tokens they represent through this projection, we identify patterns in the information flow inside the attention mechanism. Based on our discoveries, we create a tool to visualize a forward pass of Generative Pre-trained Transformers (GPTs) as an interactive flow graph, with nodes representing neurons or hidden states and edges representing the interactions between them. Our visualization simplifies huge amounts of data into easy-to-read plots that can reflect the models’ internal processing, uncovering the contribution of each component to the models’ final prediction. Our visualization also unveils new insights about the role of layer norms as semantic filters that influence the models’ output, and about neurons that are always activated during forward passes and act as regularization vectors.
Transitioning Representations between Languages for Cross-lingual Event Detection via Langevin Dynamics
PDF ↗Cross-lingual transfer learning (CLTL) for event detection (ED) aims to develop models in high-resource source languages that can be directly applied to produce effective performance for lower-resource target languages. Previous research in this area has focused on representation matching methods to develop a language-universal representation space into which source- and target-language example representations can be mapped to achieve cross-lingual transfer. However, as this approach modifies the representations for the source-language examples, the models might lose discriminative features for ED that are learned over training data of the source language to prevent effective predictions. To this end, our work introduces a novel approach for cross-lingual ED where we only aim to transition the representations for the target-language examples into the source-language space, thus preserving the representations in the source language and their discriminative information. Our method introduces Langevin Dynamics to perform representation transition and a semantic preservation framework to retain event type features during the transition process. Extensive experiments over three languages demonstrate the state-of-the-art performance for ED in CLTL.
Authorship verification (AV) is a fundamental task in natural language processing (NLP) and computational linguistics, with applications in forensic analysis, plagiarism detection, and identification of deceptive content. Existing AV techniques, including traditional stylometric and deep learning approaches, face limitations in terms of data requirements and lack of explainability. To address these limitations, this paper proposes PromptAV, a novel technique that leverages Large-Language Models (LLMs) for AV by providing step-by-step stylometric explanation prompts. PromptAV outperforms state-of-the-art baselines, operates effectively with limited training data, and enhances interpretability through intuitive explanations, showcasing its potential as an effective and interpretable solution for the AV task.
Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit linear scaling in memory and computational requirements but struggle to match the same performance as Transformers due to limitations in parallelization and scalability. We propose a novel model architecture, Receptance Weighted Key Value (RWKV), that combines the efficient parallelizable training of transformers with the efficient inference of RNNs. Our approach leverages a linear attention mechanism and allows us to formulate the model as either a Transformer or an RNN, thus parallelizing computations during training and maintains constant computational and memory complexity during inference. We scale our models as large as 14 billion parameters, by far the largest dense RNN ever trained, and find RWKV performs on par with similarly sized Transformers, suggesting future work can leverage this architecture to create more efficient models. This work presents a significant step towards reconciling trade-offs between computational efficiency and model performance in sequence processing tasks.
Dialogue models are able to generate coherent and fluent responses, but they can still be challenging to control and may produce non-engaging, unsafe results. This unpredictability diminishes user trust and can hinder the use of the models in the real world. To address this, we introduce DialGuide, a novel framework for controlling dialogue model behavior using natural language rules, or guidelines. These guidelines provide information about the context they are applicable to and what should be included in the response, allowing the models to generate responses that are more closely aligned with the developer’s expectations and intent. We evaluate DialGuide on three tasks in open-domain dialogue response generation: guideline selection, response generation, and response entailment verification. Our dataset contains 10,737 positive and 15,467 negative dialogue context-response-guideline triplets across two domains - chit-chat and safety. We provide baseline models for the tasks and benchmark their performance. We also demonstrate that DialGuide is effective in the dialogue safety domain, producing safe and engaging responses that follow developer guidelines.
We investigate the ability of transformer models to approximate the CKY algorithm, using them to directly predict a sentence’s parse and thus avoid the CKY algorithm’s cubic dependence on sentence length. We find that on standard constituency parsing benchmarks this approach achieves competitive or better performance than comparable parsers that make use of CKY, while being faster. We also evaluate the viability of this approach for parsing under random PCFGs. Here we find that performance declines as the grammar becomes more ambiguous, suggesting that the transformer is not fully capturing the CKY computation. However, we also find that incorporating additional inductive bias is helpful, and we propose a novel approach that makes use of gradients with respect to chart representations in predicting the parse, in analogy with the CKY algorithm being a subgradient of a partition function variant with respect to the chart.
Text classification is a well-studied and versatile building block for many NLP applications. Yet, existing approaches require either large annotated corpora to train a model with or, when using large language models as a base, require carefully crafting the prompt as well as using a long context that can fit many examples. As a result, it is not possible for end-users to build classifiers for themselves. To address this issue, we propose a novel approach to few-shot text classification using an LLM. Rather than few-shot examples, the LLM is prompted with descriptions of the salient features of each class. These descriptions are coauthored by the user and the LLM interactively: while the user annotates each few-shot example, the LLM asks relevant questions that the user answers. Examples, questions, and answers are summarized to form the classification prompt. Our experiments show that our approach yields high accuracy classifiers, within 79% of the performance of models trained with significantly larger datasets while using only 1% of their training sets. Additionally, in a study with 30 participants, we show that end-users are able to build classifiers to suit their specific needs. The personalized classifiers show an average accuracy of 90%, which is 15% higher than the state-of-the-art approach.
Dual use, the intentional, harmful reuse of technology and scientific artefacts, is an ill-defined problem within the context of Natural Language Processing (NLP). As large language models (LLMs) have advanced in their capabilities and become more accessible, the risk of their intentional misuse becomes more prevalent. To prevent such intentional malicious use, it is necessary for NLP researchers and practitioners to understand and mitigate the risks of their research. Hence, we present an NLP-specific definition of dual use informed by researchers and practitioners in the field. Further, we propose a checklist focusing on dual-use in NLP, that can be integrated into existing conference ethics-frameworks. The definition and checklist are created based on a survey of NLP researchers and practitioners.
Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization
PDF ↗Large language models (LLMs) have exhibited considerable cross-lingual generalization abilities, whereby they implicitly transfer knowledge across languages. However, the transfer is not equally successful for all languages, especially for low-resource ones, which poses an ongoing challenge. It is unclear whether we have reached the limits of implicit cross-lingual generalization and if explicit knowledge transfer is viable. In this paper, we investigate the potential for explicitly aligning conceptual correspondence between languages to enhance cross-lingual generalization. Using the syntactic aspect of language as a testbed, our analyses of 43 languages reveal a high degree of alignability among the spaces of structural concepts within each language for both encoder-only and decoder-only LLMs. We then propose a meta-learning-based method to learn to align conceptual spaces of different languages, which facilitates zero-shot and few-shot generalization in concept classification and also offers insights into the cross-lingual in-context learning phenomenon. Experiments on syntactic analysis tasks show that our approach achieves competitive results with state-of-the-art methods and narrows the performance gap between languages, particularly benefiting those with limited resources.
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.
Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?
PDF ↗Large Language Models (LLMs), such as ChatGPT, have drawn a lot of attentions recently in the legal domain due to its emergent ability to tackle a variety of legal tasks. However, it is still unknown if LLMs are able to analyze a legal case and perform reasoning in the same manner as lawyers. Therefore, we constructed a novel corpus consisting of scenarios pertain to Contract Acts Malaysia and Australian Social Act for Dependent Child. ChatGPT is applied to perform analysis on the corpus using the IRAC method, which is a framework widely used by legal professionals for organizing legal analysis. Each scenario in the corpus is annotated with a complete IRAC analysis in a semi-structured format so that both machines and legal professionals are able to interpret and understand the annotations. In addition, we conducted the first empirical assessment of ChatGPT for IRAC analysis in order to understand how well it aligns with the analysis of legal professionals. Our experimental results shed lights on possible future research directions to improve alignments between LLMs and legal experts in terms of legal reasoning.
Chatbots have the risk of generating offensive utterances, which must be avoided. Post-deployment, one way for a chatbot to continuously improve is to source utterance/label pairs from feedback by live users. However, among users are trolls, who provide training examples with incorrect labels. To de-troll training data, previous work removed training examples that have high user-aggregated cross-validation (CV) error. However, CV is expensive; and in a coordinated attack, CV may be overwhelmed by trolls in number and in consistency among themselves. In the present work, I address both limitations by proposing a solution inspired by methodology in automated essay scoring (AES): have multiple users rate each utterance, then perform latent class analysis (LCA) to infer correct labels. As it does not require GPU computations, LCA is inexpensive. In experiments, I found that the AES-like solution can infer training labels with high accuracy when trolls are consistent, even when trolls are the majority.
While large models such as GPT-3 demonstrate exceptional performance in zeroshot and fewshot summarization tasks, their extensive serving and fine-tuning costs hinder their utilization in various applications. Conversely, previous studies have found that although automatic metrics tend to favor smaller fine-tuned models, the quality of the summaries they generate is inferior to that of larger models like GPT-3 when assessed by human evaluators. To address this issue, we propose InheritSumm, a versatile and compact summarization model derived from GPT-3.5 through distillation. InheritSumm not only exhibits comparable zeroshot and fewshot summarization capabilities to GPT-3.5 but is also sufficiently compact for fine-tuning purposes. Experimental results demonstrate that InheritSumm achieves similar or superior performance to GPT-3.5 in zeroshot and fewshot settings. Furthermore, it outperforms the previously established best small models in both prefix-tuning and full-data fine-tuning scenarios.
A growing area of research investigates augmenting language models with tools (e.g., search engines, calculators) to overcome their shortcomings (e.g., missing or incorrect knowledge, incorrect logical inferences). Various few-shot tool-usage strategies have been proposed. However, there is no systematic and fair comparison across different strategies, or between these strategies and strong baselines that do not leverage tools. We conduct an extensive empirical analysis, finding that (1) across various datasets, example difficulty levels, and models, strong no-tool baselines are competitive to tool-assisted strategies, implying that effectively using tools with in-context demonstrations is a difficult unsolved problem; (2) for knowledge-retrieval tasks, strategies that *refine* incorrect outputs with tools outperform strategies that retrieve relevant information *ahead of* or *during generation*; (3) tool-assisted strategies are expensive in the number of tokens they require to work—incurring additional costs by orders of magnitude—which does not translate into significant improvement in performance. Overall, our findings suggest that few-shot tool integration is still an open challenge, emphasizing the need for comprehensive evaluations of future strategies to accurately assess their *benefits* and *costs*.
The Vietnamese language embodies dialectal variants closely attached to the nation’s three macro-regions: the Northern, Central and Southern regions. As the northern dialect forms the basis of the standard language, it’s considered the prestige dialect. While the northern dialect differs from the remaining two in certain aspects, it almost shares an identical lexicon with the southern dialect, making the textual attributes nearly interchangeable. In contrast, the central dialect possesses a number of unique vocabularies and is less mutually intelligible to the standard dialect. Through preliminary experiments, we observe that current NLP models do not possess understandings of the Vietnamese central dialect text, which most likely originates from the lack of resources. To facilitate research on this domain, we introduce a new parallel corpus for Vietnamese central-northern dialect text transfer. Via exhaustive benchmarking, we discover monolingual language models’ superiority over their multilingual counterparts on the dialect transfer task. We further demonstrate that fine-tuned transfer models can seamlessly improve the performance of existing NLP systems on the central dialect domain with dedicated results in translation and text-image retrieval tasks.
The common practice for assessing automatic evaluation metrics is to measure the correlation between their induced system rankings and those obtained by reliable human evaluation, where a higher correlation indicates a better metric. Yet, an intricate setting arises when an NLP task is evaluated by multiple Quality Criteria (QCs), like for text summarization where prominent criteria including relevance, consistency, fluency and coherence. In this paper, we challenge the soundness of this methodology when multiple QCs are involved, concretely for the summarization case. First, we show that the allegedly best metrics for certain QCs actually do not perform well, failing to detect even drastic summary corruptions with respect to the considered QC. To explain this, we show that some of the high correlations obtained in the multi-QC setup are spurious. Finally, we propose a procedure that may help detecting this effect. Overall, our findings highlight the need for further investigating metric evaluation methodologies for the multiple-QC case.
Text normalization methods have been commonly applied to historical language or user-generated content, but less often to dialectal transcriptions. In this paper, we introduce dialect-to-standard normalization – i.e., mapping phonetic transcriptions from different dialects to the orthographic norm of the standard variety – as a distinct sentence-level character transduction task and provide a large-scale analysis of dialect-to-standard normalization methods. To this end, we compile a multilingual dataset covering four languages: Finnish, Norwegian, Swiss German and Slovene. For the two biggest corpora, we provide three different data splits corresponding to different use cases for automatic normalization. We evaluate the most successful sequence-to-sequence model architectures proposed for text normalization tasks using different tokenization approaches and context sizes. We find that a character-level Transformer trained on sliding windows of three words works best for Finnish, Swiss German and Slovene, whereas the pre-trained byT5 model using full sentences obtains the best results for Norwegian. Finally, we perform an error analysis to evaluate the effect of different data splits on model performance.
Traditionally, large language models have been either trained on general web crawls or domain-specific data. However, recent successes of generative large language models, have shed light on the benefits of cross-domain datasets. To examine the significance of prioritizing data diversity over quality, we present a German dataset comprising texts from five domains, along with another dataset aimed at containing high-quality data. Through training a series of models ranging between 122M and 750M parameters on both datasets, we conduct a comprehensive benchmark on multiple downstream tasks. Our findings demonstrate that the models trained on the cross-domain dataset outperform those trained on quality data alone, leading to improvements up to 4.45% over the previous state-of-the-art.
Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification
PDF ↗Recently, prompt-based fine-tuning has garnered considerable interest as a core technique for few-shot text classification task. This approach reformulates the fine-tuning objective to align with the Masked Language Modeling (MLM) objective. Leveraging unlabeled data, prompt-based self-training has shown greater effectiveness in binary and three-class classification. However, prompt-based self-training for multi-class classification has not been adequately investigated, despite its significant applicability to real-world scenarios. Moreover, extending current methods to multi-class classification suffers from the verbalizer that extracts the predicted value of manually pre-defined single label word for each class from MLM predictions. Consequently, we introduce a novel, efficient verbalizer structure, named Mapping-free Automatic Verbalizer (MAV). Comprising two fully connected layers, MAV serves as a trainable verbalizer that automatically extracts the requisite word features for classification by capitalizing on all available information from MLM predictions. Experimental results on five multi-class classification datasets indicate MAV’s superior self-training efficacy.