"Merge Conflicts!" Exploring the Impacts of External Distractors to Parametric Knowledge Graphs

Large language models (LLMs) acquire extensive knowledge during pre-training, known as their parametric knowledge. However, in order to remain up-to-date and align with human instructions, LLMs inevitably require external knowledge during their interactions with users. This raises a crucial question: How will LLMs respond when external knowledge interferes with their parametric knowledge? To investigate this question, we propose a framework that systematically elicits LLM parametric knowledge and introduces external knowledge. Specifically, we uncover the impacts by constructing a parametric knowledge graph to reveal the different knowledge structures of LLMs, and introduce external knowledge through distractors of varying degrees, methods, positions, and formats. Our experiments on both black-box and open-source models demonstrate that LLMs tend to produce responses that deviate from their parametric knowledge, particularly when they encounter direct conflicts or confounding changes of information within detailed contexts. We also find that while LLMs are sensitive to the veracity of external knowledge, they can still be distracted by unrelated information. These findings highlight the risk of hallucination when integrating external knowledge, even indirectly, during interactions with current LLMs. All the data and results are publicly available.

Thrust: Adaptively Propels Large Language Models with External Knowledge

Although large-scale pre-trained language models (PTLMs) are shown to encode rich knowledge in their model parameters, the inherent knowledge in PTLMs can be opaque or static, making external knowledge necessary. However, the existing information retrieval techniques could be costly and may even introduce noisy and sometimes misleading knowledge. To address these challenges, we propose the instance-level adaptive propulsion of external knowledge (IAPEK), where we only conduct the retrieval when necessary. To achieve this goal, we propose measuring whether a PTLM contains enough knowledge to solve an instance with a novel metric, Thrust, which leverages the representation distribution of a small number of seen instances. Extensive experiments demonstrate that thrust is a good measurement of PTLM models' instance-level knowledgeability. Moreover, we can achieve significantly higher cost-efficiency with the Thrust score as the retrieval indicator than the naive usage of external knowledge on 88% of the evaluated tasks with 26% average performance improvement. Such findings shed light on the real-world practice of knowledge-enhanced LMs with a limited knowledge-seeking budget due to computation latency or costs.

On Measuring the Intrinsic Few-Shot Hardness of Datasets

While advances in pre-training have led to dramatic improvements in few-shot learning of NLP tasks, there is limited understanding of what drives successful few-shot adaptation in datasets. In particular, given a new dataset and a pre-trained model, what properties of the dataset make it \emph{few-shot learnable} and are these properties independent of the specific adaptation techniques used? We consider an extensive set of recent few-shot learning methods, and show that their performance across a large number of datasets is highly correlated, showing that few-shot hardness may be intrinsic to datasets, for a given pre-trained model. To estimate intrinsic few-shot hardness, we then propose a simple and lightweight metric called "Spread" that captures the intuition that few-shot learning is made possible by exploiting feature-space invariances between training and test samples. Our metric better accounts for few-shot hardness compared to existing notions of hardness, and is ~8-100x faster to compute.

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 442 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

Weakly Supervised Text Classification using Supervision Signals from a Language Model

Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision signals. We design a prompt which combines the document itself and "this article is talking about [MASK]." A masked language model can generate words for the [MASK] token. The generated words which summarize the content of a document can be utilized as supervision signals. We propose a latent variable model to learn a word distribution learner which associates generated words to pre-defined categories and a document classifier simultaneously without using any annotated data. Evaluation on three datasets, AGNews, 20Newsgroups, and UCINews, shows that our method can outperform baselines by 2%, 4%, and 3%.

Learning Contextual Causality from Time-consecutive Images

Causality knowledge is crucial for many artificial intelligence systems. Conventional textual-based causality knowledge acquisition methods typically require laborious and expensive human annotations. As a result, their scale is often limited. Moreover, as no context is provided during the annotation, the resulting causality knowledge records (e.g., ConceptNet) typically do not take the context into consideration. To explore a more scalable way of acquiring causality knowledge, in this paper, we jump out of the textual domain and investigate the possibility of learning contextual causality from the visual signal. Compared with pure text-based approaches, learning causality from the visual signal has the following advantages: (1) Causality knowledge belongs to the commonsense knowledge, which is rarely expressed in the text but rich in videos; (2) Most events in the video are naturally time-ordered, which provides a rich resource for us to mine causality knowledge from; (3) All the objects in the video can be used as context to study the contextual property of causal relations. In detail, we first propose a high-quality dataset Vis-Causal and then conduct experiments to demonstrate that with good language and visual representation models as well as enough training signals, it is possible to automatically discover meaningful causal knowledge from the videos. Further analysis also shows that the contextual property of causal relations indeed exists, taking which into consideration might be crucial if we want to use the causality knowledge in real applications, and the visual signal could serve as a good resource for learning such contextual causality.

A Brief Survey and Comparative Study of Recent Development of Pronoun Coreference Resolution

Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to. Compared with the general coreference resolution task, the main challenge of PCR is the coreference relation prediction rather than the mention detection. As one important natural language understanding (NLU) component, pronoun resolution is crucial for many downstream tasks and still challenging for existing models, which motivates us to survey existing approaches and think about how to do better. In this survey, we first introduce representative datasets and models for the ordinary pronoun coreference resolution task. Then we focus on recent progress on hard pronoun coreference resolution problems (e.g., Winograd Schema Challenge) to analyze how well current models can understand commonsense. We conduct extensive experiments to show that even though current models are achieving good performance on the standard evaluation set, they are still not ready to be used in real applications (e.g., all SOTA models struggle on correctly resolving pronouns to infrequent objects). All experiment codes are available at https://github.com/HKUST-KnowComp/PCR.

WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge

In this paper, we present the first comprehensive categorization of essential commonsense knowledge for answering the Winograd Schema Challenge (WSC). For each of the questions, we invite annotators to first provide reasons for making correct decisions and then categorize them into six major knowledge categories. By doing so, we better understand the limitation of existing methods (i.e., what kind of knowledge cannot be effectively represented or inferred with existing methods) and shed some light on the commonsense knowledge that we need to acquire in the future for better commonsense reasoning. Moreover, to investigate whether current WSC models can understand the commonsense or they simply solve the WSC questions based on the statistical bias of the dataset, we leverage the collected reasons to develop a new task called WinoWhy, which requires models to distinguish plausible reasons from very similar but wrong reasons for all WSC questions. Experimental results prove that even though pre-trained language representation models have achieved promising progress on the original WSC dataset, they are still struggling at WinoWhy. Further experiments show that even though supervised models can achieve better performance, the performance of these models can be sensitive to the dataset distribution. WinoWhy and all codes are available at: https://github.com/HKUST-KnowComp/WinoWhy.