We present SeaEval, a benchmark for multilingual foundation models. In addition to characterizing how these models understand and reason with natural language, we also investigate how well they comprehend cultural practices, nuances, and values. Alongside standard accuracy metrics, we investigate the brittleness of foundation models in the dimensions of semantics and multilinguality. Our analyses span both open-sourced and closed models, leading to empirical results across classic NLP tasks, reasoning, and cultural comprehension. Key findings indicate (1) Many models exhibit varied behavior when given paraphrased instructions. (2) Many models still suffer from exposure bias (e.g., positional bias, majority label bias). (3) For questions rooted in factual, scientific, and commonsense knowledge, consistent responses are expected across multilingual queries that are semantically equivalent. Yet, most models surprisingly demonstrate inconsistent performance on these queries. (4) Multilingually-trained models have not attained “balanced multilingual” capabilities. Our endeavors underscore the need for more generalizable semantic representations and enhanced multilingual contextualization. SeaEval can serve as a launchpad for more thorough investigations and evaluations for multilingual and multicultural scenarios.

This paper describes our submission to the fifth track of the 11th Dialog System Technology Challenge (DSTC-11), which focuses on “Task-oriented Conversational Modeling with Subjective Knowledge”. We focus on response generation and leverage a ranking strategy to ensemble individual models of BART, Long-T5, and a fine-tuned large language model based on LLaMA. The strategy is supplemented by other techniques like low rank adaptation to maintain efficient utilization of these large models while still achieving optimal performance. The experiments show that the ensemble method outperforms individual models and the baseline method. Our model was ranked 1st place in ROUGE_1, 2nd place in ROUGE_L score and 4th place in human evaluation among a total of 14 participating teams.

Transformer-based language models such as BERT (CITATION) have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use various heuristics to successively shorten sequence length while transforming tokens through encoders, in tasks such as classification and ranking that require a single token embedding for prediction. We present a novel solution to this problem, called Pyramid-BERT where we replace previously used heuristics with a core-set based token selection method justified by theoretical results. The core-set based token selection technique allows us to avoid expensive pre-training, gives a space-efficient fine tuning, and thus makes it suitable to handle longer sequence lengths. We provide extensive experiments establishing advantages of pyramid BERT over several baselines and existing works on the GLUE benchmarks and Long Range Arena (CITATION) datasets.

Complex question answering over knowledge base remains as a challenging task because it involves reasoning over multiple pieces of information, including intermediate entities/relations and other constraints. Previous methods simplify the SPARQL query of a question into such forms as a list or a graph, missing such constraints as “filter” and “order_by”, and present models specialized for generating those simplified forms from a given question. We instead introduce a novel approach that directly generates an executable SPARQL query without simplification, addressing the issue of generating unseen entities. We adapt large scale pre-trained encoder-decoder models and show that our method significantly outperforms the previous methods and also that our method has higher interpretability and computational efficiency than the previous methods.

Although deep neural networks are effective at extracting high-level features, classification methods usually encode an input into a vector representation via simple feature aggregation operations (e.g. pooling). Such operations limit the performance. For instance, a multi-label document may contain several concepts. In this case, one vector can not sufficiently capture its salient and discriminative content. Thus, we propose Hyperbolic Capsule Networks (HyperCaps) for Multi-Label Classification (MLC), which have two merits. First, hyperbolic capsules are designed to capture fine-grained document information for each label, which has the ability to characterize complicated structures among labels and documents. Second, Hyperbolic Dynamic Routing (HDR) is introduced to aggregate hyperbolic capsules in a label-aware manner, so that the label-level discriminative information can be preserved along the depth of neural networks. To efficiently handle large-scale MLC datasets, we additionally present a new routing method to adaptively adjust the capsule number during routing. Extensive experiments are conducted on four benchmark datasets. Compared with the state-of-the-art methods, HyperCaps significantly improves the performance of MLC especially on tail labels.

Multi-label text classification (MLTC) aims to tag most relevant labels for the given document. In this paper, we propose a Label-Specific Attention Network (LSAN) to learn a label-specific document representation. LSAN takes advantage of label semantic information to determine the semantic connection between labels and document for constructing label-specific document representation. Meanwhile, the self-attention mechanism is adopted to identify the label-specific document representation from document content information. In order to seamlessly integrate the above two parts, an adaptive fusion strategy is proposed, which can effectively output the comprehensive label-specific document representation to build multi-label text classifier. Extensive experimental results demonstrate that LSAN consistently outperforms the state-of-the-art methods on four different datasets, especially on the prediction of low-frequency labels. The code and hyper-parameter settings are released to facilitate other researchers.