Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this work, we extend the idea to open response generation, by integrating voting into the decoding method. Each output sentence is selected from among multiple samples, conditioning on the previous selections, based on a simple token overlap score. We compare this "Sample & Select" method to greedy decoding, beam search, nucleus sampling, and the recently introduced hallucination avoiding decoders of DoLA, P-CRR, and S-CRR. We show that Sample & Select improves factuality by a 30% relative margin against these decoders in NLI-based evaluation on the subsets of CNN/DM and XSum used in the FRANK benchmark, while maintaining comparable ROUGE-1 F1 scores against reference summaries. We collect human verifications of the generated summaries, confirming the factual superiority of our method.
With the widespread adoption of large language models (LLMs) in numerous applications, the challenge of factuality and the propensity for hallucinations raises significant concerns. To address this issue, particularly in retrieval-augmented in-context learning, we introduce the hierarchical graph of thoughts (HGOT), a structured, multi-layered graph approach designed to enhance the retrieval of pertinent passages during in-context learning. The framework utilizes the emergent planning capabilities of LLMs, employing the divide-and-conquer strategy to break down complex queries into manageable sub-queries. It refines self-consistency majority voting for answer selection, which incorporates the recently proposed citation recall and precision metrics to assess the quality of thoughts, linking an answer's credibility intrinsically to the thought's quality. This methodology introduces a weighted system in majority voting, prioritizing answers based on the citation quality of their thoughts. Additionally, we propose a scoring mechanism for evaluating retrieved passages, considering factors such as citation frequency and quality, self-consistency confidence, and the retrieval module's ranking. Experiments reveal that HGOT outperforms other retrieval-augmented in-context learning methods, including Demonstrate-Search-Predict (DSP), ReAct, Self-Ask, and Retrieve-then-Read on different datasets by as much as $7\%$, demonstrating its efficacy in enhancing the factuality of LLMs.
Reasoning is a fundamental component for achieving language understanding. Among the multiple types of reasoning, conditional reasoning, the ability to draw different conclusions depending on some condition, has been understudied in large language models (LLMs). Recent prompting methods, such as chain of thought, have significantly improved LLMs on reasoning tasks. Nevertheless, there is still little understanding of what triggers reasoning abilities in LLMs. We hypothesize that code prompts can trigger conditional reasoning in LLMs trained on text and code. We propose a chain of prompts that transforms a natural language problem into code and prompts the LLM with the generated code. Our experiments find that code prompts exhibit a performance boost between 2.6 and 7.7 points on GPT 3.5 across multiple datasets requiring conditional reasoning. We then conduct experiments to discover how code prompts elicit conditional reasoning abilities and through which features. We observe that prompts need to contain natural language text accompanied by high-quality code that closely represents the semantics of the instance text. Furthermore, we show that code prompts are more efficient, requiring fewer demonstrations, and that they trigger superior state tracking of variables or key entities.
We introduce a new framework of adversarial attacks, named calibration attacks, in which the attacks are generated and organized to trap victim models to be miscalibrated without altering their original accuracy, hence seriously endangering the trustworthiness of the models and any decision-making based on their confidence scores. Specifically, we identify four novel forms of calibration attacks: underconfidence attacks, overconfidence attacks, maximum miscalibration attacks, and random confidence attacks, in both the black-box and white-box setups. We then test these new attacks on typical victim models with comprehensive datasets, demonstrating that even with a relatively low number of queries, the attacks can create significant calibration mistakes. We further provide detailed analyses to understand different aspects of calibration attacks. Building on that, we investigate the effectiveness of widely used adversarial defences and calibration methods against these types of attacks, which then inspires us to devise two novel defences against such calibration attacks.
Understanding the progression of cancer is crucial for defining treatments for patients. The objective of this study is to automate the detection of metastatic liver disease from free-style computed tomography (CT) radiology reports. Our research demonstrates that transferring knowledge using three approaches can improve model performance. First, we utilize generic language models (LMs), pretrained in a self-supervised manner. Second, we use a semi-supervised approach to train our model by automatically annotating a large unlabeled dataset; this approach substantially enhances the model's performance. Finally, we transfer knowledge from related tasks by designing a multi-task transfer learning methodology. We leverage the recent advancement of parameter-efficient LM adaptation strategies to improve performance and training efficiency. Our dataset consists of CT reports collected at Memorial Sloan Kettering Cancer Center (MSKCC) over the course of 12 years. 2,641 reports were manually annotated by domain experts; among them, 841 reports have been annotated for the presence of liver metastases. Our best model achieved an F1-score of 73.8%, a precision of 84%, and a recall of 65.8%.
Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models. This study aims at assessing the financial reasoning capabilities of LLMs. We leverage mock exam questions of the Chartered Financial Analyst (CFA) Program to conduct a comprehensive evaluation of ChatGPT and GPT-4 in financial analysis, considering Zero-Shot (ZS), Chain-of-Thought (CoT), and Few-Shot (FS) scenarios. We present an in-depth analysis of the models' performance and limitations, and estimate whether they would have a chance at passing the CFA exams. Finally, we outline insights into potential strategies and improvements to enhance the applicability of LLMs in finance. In this perspective, we hope this work paves the way for future studies to continue enhancing LLMs for financial reasoning through rigorous evaluation.
We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data. We observe that existing unsupervised parsers capture differing aspects of parsing structures, which can be leveraged to enhance unsupervised parsing performance. To this end, we propose a notion of "tree averaging," based on which we further propose a novel ensemble method for unsupervised parsing. To improve inference efficiency, we further distill the ensemble knowledge into a student model; such an ensemble-then-distill process is an effective approach to mitigate the over-smoothing problem existing in common multi-teacher distilling methods. Experiments show that our method surpasses all previous approaches, consistently demonstrating its effectiveness and robustness across various runs, with different ensemble components, and under domain-shift conditions.
Open intent detection, a crucial aspect of natural language understanding, involves the identification of previously unseen intents in user-generated text. Despite the progress made in this field, challenges persist in handling new combinations of language components, which is essential for compositional generalization. In this paper, we present a case study exploring the use of ChatGPT as a data augmentation technique to enhance compositional generalization in open intent detection tasks. We begin by discussing the limitations of existing benchmarks in evaluating this problem, highlighting the need for constructing datasets for addressing compositional generalization in open intent detection tasks. By incorporating synthetic data generated by ChatGPT into the training process, we demonstrate that our approach can effectively improve model performance. Rigorous evaluation of multiple benchmarks reveals that our method outperforms existing techniques and significantly enhances open intent detection capabilities. Our findings underscore the potential of large language models like ChatGPT for data augmentation in natural language understanding tasks.
Reasoning has been a central topic in artificial intelligence from the beginning. The recent progress made on distributed representation and neural networks continues to improve the state-of-the-art performance of natural language inference. However, it remains an open question whether the models perform real reasoning to reach their conclusions or rely on spurious correlations. Adversarial attacks have proven to be an important tool to help evaluate the Achilles' heel of the victim models. In this study, we explore the fundamental problem of developing attack models based on logic formalism. We propose NatLogAttack to perform systematic attacks centring around natural logic, a classical logic formalism that is traceable back to Aristotle's syllogism and has been closely developed for natural language inference. The proposed framework renders both label-preserving and label-flipping attacks. We show that compared to the existing attack models, NatLogAttack generates better adversarial examples with fewer visits to the victim models. The victim models are found to be more vulnerable under the label-flipping setting. NatLogAttack provides a tool to probe the existing and future NLI models' capacity from a key viewpoint and we hope more logic-based attacks will be further explored for understanding the desired property of reasoning.
In recent years, large language models (LLMs) have achieved strong performance on benchmark tasks, especially in zero or few-shot settings. However, these benchmarks often do not adequately address the challenges posed in the real-world, such as that of hierarchical classification. In order to address this challenge, we propose refactoring conventional tasks on hierarchical datasets into a more indicative long-tail prediction task. We observe LLMs are more prone to failure in these cases. To address these limitations, we propose the use of entailment-contradiction prediction in conjunction with LLMs, which allows for strong performance in a strict zero-shot setting. Importantly, our method does not require any parameter updates, a resource-intensive process and achieves strong performance across multiple datasets.