Cognitive research indicates that abstraction ability is essential in human intelligence, which remains under-explored in language models. In this paper, we present AbsPyramid, a unified entailment graph of 221K textual descriptions of abstraction knowledge. While existing resources only touch nouns or verbs within simplified events or specific domains, AbsPyramid collects abstract knowledge for three components of diverse events to comprehensively evaluate the abstraction ability of language models in the open domain. Experimental results demonstrate that current LLMs face challenges comprehending abstraction knowledge in zero-shot and few-shot settings. By training on our rich abstraction knowledge, we find LLMs can acquire basic abstraction abilities and generalize to unseen events. In the meantime, we empirically show that our benchmark is comprehensive to enhance LLMs across two previous abstraction tasks.

Lateral thinking is essential in breaking away from conventional thought patterns and finding innovative solutions to problems. Despite this, language models often struggle with reasoning tasks that require lateral thinking. In this paper, we present our system for SemEval-2024 Task 9’s BrainTeaser challenge, which requires language models to answer brain teaser questions that typically involve lateral reasoning scenarios. Our framework is based on large language models and incorporates a zero-shot prompting method that integrates conceptualizations of automatically detected instances in the question. We also transform the task of question answering into a declarative format to enhance the discriminatory ability of large language models. Our zero-shot evaluation results with ChatGPT indicate that our approach outperforms baselines, including zero-shot and few-shot prompting and chain-of-thought reasoning. Additionally, our system ranks ninth on the official leaderboard, demonstrating its strong performance.

Sign Language Translation (SLT) is a complex task that involves accurately interpreting sign language gestures and translating them into spoken or written language and vice versa. Its primary objective is to facilitate communication between individuals with hearing difficulties using deep learning systems. Existing approaches leverage gloss annotations of sign language gestures to assist the model in capturing the movement and differentiating various gestures. However, constructing a large-scale gloss-annotated dataset is both expensive and impractical to cover multiple languages, and pre-trained generative models cannot be efficiently used due to the lack of textual source context in SLT. To address these challenges, we propose a gloss-free framework for the WMT23 SLT task. Our system primarily consists of a visual extractor for extracting video embeddings and a generator responsible for producing the translated text. We also employ an embedding alignment block that is trained to align the embedding space of the visual extractor with that of the generator. Despite undergoing extensive training and validation, our system consistently falls short of meeting the baseline performance. Further analysis shows that our model’s poor projection rate prevents it from learning diverse visual embeddings. Our codes and model checkpoints are available at https://github.com/HKUST-KnowComp/SLT.

The NLP community has recently witnessed the success of Large Language Models (LLMs) across various Natural Language Processing (NLP) tasks. However, the potential of LLMs for word-level auto-completion in a multilingual context has not been thoroughly explored yet. To address this gap and benchmark the performance of LLMs, we propose an LLM-based system for the WMT23 Word-Level Auto-Completion (WLAC) task. Our system utilizes ChatGPT to represent LLMs and evaluates its performance in three translation directions: Chinese-English, German-English, and English-German. We also study the task under zero-shot and few-shot settings to assess the potential benefits of incorporating exemplars from the training set in guiding the LLM to perform the task. The results of our experiments show that, on average, our system attains a 29.8% accuracy on the test set. Further analyses reveal that LLMs struggle with WLAC in the zero-shot setting, but performance significantly improves with the help of additional exemplars, though some common errors still appear frequently. These findings have important implications for incorporating LLMs into computer-aided translation systems, as they can potentially enhance the quality of translations. Our codes for evaluation are available at https://github.com/ethanyiwu/WLAC.

A main goal of Argument Mining (AM) is to analyze an author’s stance. Unlike previous AM datasets focusing only on text, the shared task at the 10th Workshop on Argument Mining introduces a dataset including both texts and images. Importantly, these images contain both visual elements and optical characters. Our new framework, TILFA (A Unified Framework for Text, Image, and Layout Fusion in Argument Mining), is designed to handle this mixed data. It excels at not only understanding text but also detecting optical characters and recognizing layout details in images. Our model significantly outperforms existing baselines, earning our team, KnowComp, the 1st place in the leaderboard of Argumentative Stance Classification subtask in this shared task.

Relation extraction is often challenged by insufficient labeled data. Previous methods exploit knowledge from unlabeled data by generating pseudo labels in a self-training pipeline, which suffers a gradual drift problem. Logic rules, a transferable and explainable form of expert knowledge, have achieved promising success by improving the model with weak labels. But manually writing comprehensive rules set is challenging and tedious. To alleviate the human labor of writing high-quality rules, in this work, we propose ARIA, an Automatic task-specific Rules distilling framework. Specifically, we guide the pre-trained language model to reason rules as experts and compose them into robust compound rules for data labeling. Besides, ARIA could continuously enrich the rules set to power the labeling ability by discovering reliable model-labeled data for distinguishable rules generation. Experiments on two public datasets demonstrate the effectiveness of ARIA in a low-resource scenario.

Zero-shot commonsense Question-Answering (QA) requires models to reason about general situations beyond specific benchmarks. State-of-the-art approaches fine-tune language models on QA pairs constructed from CommonSense Knowledge Bases (CSKBs) to equip the models with more commonsense knowledge in a QA context. However, current QA synthesis protocols may introduce noise from the CSKBs and generate ungrammatical questions and false negative options, which impede the model’s ability to generalize. To address these issues, we propose QADYNAMICS, a training dynamics-driven framework for QA diagnostics and refinement. Our approach analyzes the training dynamics of each QA pair at both the question level and option level, discarding machine-detectable artifacts by removing uninformative QA pairs and mislabeled or false-negative options. Extensive experiments demonstrate the effectiveness of our approach, which outperforms all baselines while using only 33% of the synthetic data, even including LLMs such as ChatGPT. Moreover, expert evaluations confirm that our framework significantly improves the quality of QA synthesis. Our code and model checkpoints are available at https://github.com/HKUST-KnowComp/QaDynamics.