This paper proposes a framework for quantitatively evaluating interactive LLMs such as ChatGPT using publicly available data sets. We carry out an extensive technical evaluation of ChatGPT using 21 data sets covering 8 different common NLP application tasks. We evaluate the multitask, multilingual and multi-modal aspects of ChatGPT based on these data sets and a newly designed multimodal dataset. We find that ChatGPT outperforms LLMs with zero-shot learning on most tasks and even outperforms fine-tuned models on some tasks. We find that it is better at understanding non-Latin script languages than generating them. It is able to generate multimodal content from textual prompts, via an intermediate code generation step. Moreover, we find that ChatGPT is 64.33% accurate on average in 10 different reasoning categories under logical reasoning, non-textual reasoning, and commonsense reasoning, hence making it an unreliable reasoner. It is, for example, better at deductive than inductive reasoning. ChatGPT suffers from hallucination problems like other LLMs and it generates more extrinsic hallucinations from its parametric memory as it does not have access to an external knowledge base. Finally, the interactive feature of ChatGPT enables human collaboration with the underlying LLM to improve its performance, i.e, 8% ROUGE-1 on summarization and 2% ChrF++ on machine translation, in a multi-turn "prompt engineering" fashion.
Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which greatly hinders their application. The heterogeneity between external knowledge and dialogue context challenges representation learning and source integration, and further contributes to unfaithfulness. To handle this challenge and generate more faithful responses, this paper presents RHO ($\rho$) utilizing the representations of linked entities and relation predicates from a knowledge graph (KG). We propose (1) local knowledge grounding to combine textual embeddings with the corresponding KG embeddings; and (2) global knowledge grounding to equip RHO with multi-hop reasoning abilities via the attention mechanism. In addition, we devise a response re-ranking technique based on walks over KG sub-graphs for better conversational reasoning. Experimental results on OpenDialKG show that our approach significantly outperforms state-of-the-art methods on both automatic and human evaluation by a large margin, especially in hallucination reduction (17.54% in FeQA).
Parameter efficient learning methods (PERMs) have recently gained significant attention as they provide an efficient way for pre-trained language models (PLMs) to adapt to a downstream task. However, these conclusions are mostly drawn from in-domain evaluations over the full training set. In this paper, we present comparisons between PERMs and finetuning from three new perspectives: (1) the effect of sample and model size to in-domain evaluations, (2) generalization to unseen domains and new datasets, and (3) the faithfulness of generations. Our results show that for in-domain settings (a) there is a cross point of sample size for which PERMs will perform better than finetuning when training with fewer samples, and (b) larger PLMs have larger cross points. For cross-domain and cross-dataset cases, we show that (a) Adapter (Houlsby et al., 2019) performs the best amongst all the PERMs studied here, and (b) it outperforms finetuning if the task dataset is below a certain size. We also compare the faithfulness of generations and show that PERMs can achieve better faithfulness score than finetuning, especially for small training set, by as much as 6%. Finally, we apply Adapter to MT-NLG 530b (Smith et al., 2022) and achieve new state-of-the-art results on Xsum (Narayan et al., 2018) for all ROUGE scores (ROUGE-1 49.17, ROUGE-2 27.20, ROUGE-L 40.98).
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.
Pretrained language models (LMs) are susceptible to generate text with nonfactual information. In this work, we measure and improve the factual accuracy of large-scale LMs for open-ended text generation. We design the FactualityPrompts test set and metrics to measure the factuality of LM generations. Based on that, we study the factual accuracy of LMs with parameter sizes ranging from 126M to 530B. Interestingly, we find that larger LMs are more factual than smaller ones, although a previous study suggests that larger LMs can be less truthful in terms of misconceptions. In addition, popular sampling algorithms (e.g., top-p) in open-ended text generation can harm the factuality due to the "uniform randomness" introduced at every sampling step. We propose the factual-nucleus sampling algorithm that dynamically adapts the randomness to improve the factuality of generation while maintaining quality. Furthermore, we analyze the inefficiencies of the standard training method in learning correct associations between entities from factual text corpus (e.g., Wikipedia). We propose a factuality-enhanced training method that uses TopicPrefix for better awareness of facts and sentence completion as the training objective, which can vastly reduce the factual errors.
Considerable advancements have been made in various NLP tasks based on the impressive power of large pre-trained language models (LLMs). These results have inspired efforts to understand the limits of LLMs so as to evaluate how far we are from achieving human level general natural language understanding. In this work, we challenge the capability of LLMs with the new task of Ethical Quandary Generative Question Answering. Ethical quandary questions are more challenging to address because multiple conflicting answers may exist to a single quandary. We propose a system, AiSocrates, that provides an answer with a deliberative exchange of different perspectives to an ethical quandary, in the approach of Socratic philosophy, instead of providing a closed answer like an oracle. AiSocrates searches for different ethical principles applicable to the ethical quandary and generates an answer conditioned on the chosen principles through prompt-based few-shot learning. We also address safety concerns by providing a human controllability option in choosing ethical principles. We show that AiSocrates generates promising answers to ethical quandary questions with multiple perspectives, 6.92% more often than answers written by human philosophers by one measure, but the system still needs improvement to match the coherence of human philosophers fully. We argue that AiSocrates is a promising step toward developing an NLP system that incorporates human values explicitly by prompt instructions. We are releasing the code for research purposes.
Media framing bias can lead to increased political polarization, and thus, the need for automatic mitigation methods is growing. We propose a new task, a neutral summary generation from multiple news headlines of the varying political leanings to facilitate balanced and unbiased news reading. In this paper, we first collect a new dataset, obtain insights about framing bias through a case study, and propose a new effective metric and models for the task. Lastly, we conduct experimental analyses to provide insights about remaining challenges and future directions. One of the most interesting observations is that generation models can hallucinate not only factually inaccurate or unverifiable content, but also politically biased content.