Recent advancements in Large Language Models empower them to follow freeform instructions, including imitating generic or specific demographic personas in conversations. We define generic personas to represent demographic groups, such as "an Asian person", whereas specific personas may take the form of specific popular Asian names like "Yumi". While the adoption of personas enriches user experiences by making dialogue systems more engaging and approachable, it also casts a shadow of potential risk by exacerbating social biases within model responses, thereby causing societal harm through interactions with users. In this paper, we systematically study "persona biases", which we define to be the sensitivity of dialogue models' harmful behaviors contingent upon the personas they adopt. We categorize persona biases into biases in harmful expression and harmful agreement, and establish a comprehensive evaluation framework to measure persona biases in five aspects: Offensiveness, Toxic Continuation, Regard, Stereotype Agreement, and Toxic Agreement. Additionally, we propose to investigate persona biases by experimenting with UNIVERSALPERSONA, a systematically constructed persona dataset encompassing various types of both generic and specific model personas. Through benchmarking on four different models -- including Blender, ChatGPT, Alpaca, and Vicuna -- our study uncovers significant persona biases in dialogue systems. Our findings also underscore the pressing need to revisit the use of personas in dialogue agents to ensure safe application.

The field of drug discovery has experienced a remarkable transformation with the advent of artificial intelligence (AI) and machine learning (ML) technologies. However, as these AI and ML models are becoming more complex, there is a growing need for transparency and interpretability of the models. Explainable Artificial Intelligence (XAI) is a novel approach that addresses this issue and provides a more interpretable understanding of the predictions made by machine learning models. In recent years, there has been an increasing interest in the application of XAI techniques to drug discovery. This review article provides a comprehensive overview of the current state-of-the-art in XAI for drug discovery, including various XAI methods, their application in drug discovery, and the challenges and limitations of XAI techniques in drug discovery. The article also covers the application of XAI in drug discovery, including target identification, compound design, and toxicity prediction. Furthermore, the article suggests potential future research directions for the application of XAI in drug discovery. The aim of this review article is to provide a comprehensive understanding of the current state of XAI in drug discovery and its potential to transform the field.

Generative artificial intelligence holds enormous potential to revolutionize decision-making processes, from everyday to high-stake scenarios. However, as many decisions carry social implications, for AI to be a reliable assistant for decision-making it is crucial that it is able to capture the balance between self-interest and the interest of others. We investigate the ability of three of the most advanced chatbots to predict dictator game decisions across 108 experiments with human participants from 12 countries. We find that only GPT-4 (not Bard nor Bing) correctly captures qualitative behavioral patterns, identifying three major classes of behavior: self-interested, inequity-averse, and fully altruistic. Nonetheless, GPT-4 consistently underestimates self-interest and inequity-aversion, while overestimating altruistic behavior. This bias has significant implications for AI developers and users.

In this paper, we propose an autonomous information seeking visual question answering framework, AVIS. Our method leverages a Large Language Model (LLM) to dynamically strategize the utilization of external tools and to investigate their outputs, thereby acquiring the indispensable knowledge needed to provide answers to the posed questions. Responding to visual questions that necessitate external knowledge, such as "What event is commemorated by the building depicted in this image?", is a complex task. This task presents a combinatorial search space that demands a sequence of actions, including invoking APIs, analyzing their responses, and making informed decisions. We conduct a user study to collect a variety of instances of human decision-making when faced with this task. This data is then used to design a system comprised of three components: an LLM-powered planner that dynamically determines which tool to use next, an LLM-powered reasoner that analyzes and extracts key information from the tool outputs, and a working memory component that retains the acquired information throughout the process. The collected user behavior serves as a guide for our system in two key ways. First, we create a transition graph by analyzing the sequence of decisions made by users. This graph delineates distinct states and confines the set of actions available at each state. Second, we use examples of user decision-making to provide our LLM-powered planner and reasoner with relevant contextual instances, enhancing their capacity to make informed decisions. We show that AVIS achieves state-of-the-art results on knowledge-intensive visual question answering benchmarks such as Infoseek and OK-VQA.

This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images. Our approach extracts independent semantic components from the embeddings of a pre-trained model by leveraging anisotropic information that remains after the whitening process in Principal Component Analysis (PCA). We demonstrate that each embedding can be expressed as a composition of a few intrinsic interpretable axes and that these semantic axes remain consistent across different languages, algorithms, and modalities. The discovery of a universal semantic structure in the geometric patterns of embeddings enhances our understanding of the representations in embeddings.

Most humans use visual imagination to understand and reason about language, but models such as BERT reason about language using knowledge acquired during text-only pretraining. In this work, we investigate whether vision-and-language pretraining can improve performance on text-only tasks that involve implicit visual reasoning, focusing primarily on zero-shot probing methods. We propose a suite of visual language understanding (VLU) tasks for probing the visual reasoning abilities of text encoder models, as well as various non-visual natural language understanding (NLU) tasks for comparison. We also contribute a novel zero-shot knowledge probing method, Stroop probing, for applying models such as CLIP to text-only tasks without needing a prediction head such as the masked language modelling head of models like BERT. We show that SOTA multimodally trained text encoders outperform unimodally trained text encoders on the VLU tasks while being underperformed by them on the NLU tasks, lending new context to previously mixed results regarding the NLU capabilities of multimodal models. We conclude that exposure to images during pretraining affords inherent visual reasoning knowledge that is reflected in language-only tasks that require implicit visual reasoning. Our findings bear importance in the broader context of multimodal learning, providing principled guidelines for the choice of text encoders used in such contexts.

Numerous evaluation metrics have been developed for natural language generation tasks, but their effectiveness in evaluating stories is limited as they are not specifically tailored to assess intricate aspects of storytelling, such as fluency and interestingness. In this paper, we introduce DELTASCORE, a novel methodology that employs perturbation techniques for the evaluation of nuanced story aspects. Our central proposition posits that the extent to which a story excels in a specific aspect (e.g., fluency) correlates with the magnitude of its susceptibility to particular perturbations (e.g., the introduction of typos). Given this, we measure the quality of an aspect by calculating the likelihood difference between pre- and post-perturbation states using pre-trained language models. We compare DELTASCORE with existing metrics on storytelling datasets from two domains in five fine-grained story aspects: fluency, coherence, relatedness, logicality, and interestingness. DELTASCORE demonstrates remarkable performance, revealing a surprising finding that a specific perturbation proves highly effective in capturing multiple aspects.

Distributed representations of words encode lexical semantic information, but what type of information is encoded and how? Focusing on the skip-gram with negative-sampling method, we found that the squared norm of static word embedding encodes the information gain conveyed by the word; the information gain is defined by the Kullback-Leibler divergence of the co-occurrence distribution of the word to the unigram distribution. Our findings are explained by the theoretical framework of the exponential family of probability distributions and confirmed through precise experiments that remove spurious correlations arising from word frequency. This theory also extends to contextualized word embeddings in language models or any neural networks with the softmax output layer. We also demonstrate that both the KL divergence and the squared norm of embedding provide a useful metric of the informativeness of a word in tasks such as keyword extraction, proper-noun discrimination, and hypernym discrimination.

Selecting the right set of hyperparameters is crucial in time series forecasting. The classical temporal cross-validation framework for hyperparameter optimization (HPO) often leads to poor test performance because of a possible mismatch between validation and test periods. To address this test-validation mismatch, we propose a novel technique, H-Pro to drive HPO via test proxies by exploiting data hierarchies often associated with time series datasets. Since higher-level aggregated time series often show less irregularity and better predictability as compared to the lowest-level time series which can be sparse and intermittent, we optimize the hyperparameters of the lowest-level base-forecaster by leveraging the proxy forecasts for the test period generated from the forecasters at higher levels. H-Pro can be applied on any off-the-shelf machine learning model to perform HPO. We validate the efficacy of our technique with extensive empirical evaluation on five publicly available hierarchical forecasting datasets. Our approach outperforms existing state-of-the-art methods in Tourism, Wiki, and Traffic datasets, and achieves competitive result in Tourism-L dataset, without any model-specific enhancements. Moreover, our method outperforms the winning method of the M5 forecast accuracy competition.

Measuring the semantic similarity between two sentences is still an important task. The word mover's distance (WMD) computes the similarity via the optimal alignment between the sets of word embeddings. However, WMD does not utilize word order, making it challenging to distinguish sentences with significant overlaps of similar words, even if they are semantically very different. Here, we attempt to improve WMD by incorporating the sentence structure represented by BERT's self-attention matrix (SAM). The proposed method is based on the Fused Gromov-Wasserstein distance, which simultaneously considers the similarity of the word embedding and the SAM for calculating the optimal transport between two sentences. Experiments demonstrate the proposed method enhances WMD and its variants in paraphrase identification with near-equivalent performance in semantic textual similarity. Our code is available at \url{https://github.com/ymgw55/WSMD}.