Surging interest in deep learning from high-stakes domains has precipitated concern over the inscrutable nature of black box neural networks. Explainable AI (XAI) research has led to an abundance of explanation algorithms for these black boxes. Such post hoc explainers produce human-comprehensible explanations, however, their fidelity with respect to the model is not well understood - explanation evaluation remains one of the most challenging issues in XAI. In this paper, we ask a targeted but important question: can popular feature-additive explainers (e.g., LIME, SHAP, SHAPR, MAPLE, and PDP) explain feature-additive predictors? Herein, we evaluate such explainers on ground truth that is analytically derived from the additive structure of a model. We demonstrate the efficacy of our approach in understanding these explainers applied to symbolic expressions, neural networks, and generalized additive models on thousands of synthetic and several real-world tasks. Our results suggest that all explainers eventually fail to correctly attribute the importance of features, especially when a decision-making process involves feature interactions.

Large language models have shown breakthrough potential in many NLP domains. Here we consider their use for stylometry, specifically authorship identification in Early Modern English drama. We find both promising and concerning results; LLMs are able to accurately predict the author of surprisingly short passages but are also prone to confidently misattribute texts to specific authors. A fine-tuned t5-large model outperforms all tested baselines, including logistic regression, SVM with a linear kernel, and cosine delta, at attributing small passages. However, we see indications that the presence of certain authors in the model's pre-training data affects predictive results in ways that are difficult to assess.

Generative language models (LMs) are increasingly used for document class-prediction tasks and promise enormous improvements in cost and efficiency. Existing research often examines simple classification tasks, but the capability of LMs to classify on complex or specialized tasks is less well understood. We consider a highly complex task that is challenging even for humans: the classification of legal reasoning according to jurisprudential philosophy. Using a novel dataset of historical United States Supreme Court opinions annotated by a team of domain experts, we systematically test the performance of a variety of LMs. We find that generative models perform poorly when given instructions (i.e. prompts) equal to the instructions presented to human annotators through our codebook. Our strongest results derive from fine-tuning models on the annotated dataset; the best performing model is an in-domain model, LEGAL-BERT. We apply predictions from this fine-tuned model to study historical trends in jurisprudence, an exercise that both aligns with prominent qualitative historical accounts and points to areas of possible refinement in those accounts. Our findings generally sound a note of caution in the use of generative LMs on complex tasks without fine-tuning and point to the continued relevance of human annotation-intensive classification methods.

Despite considerable performance improvements, current conversational AI systems often fail to meet user expectations. We discuss several pragmatic limitations of current conversational AI systems. We illustrate pragmatic limitations with examples that are syntactically appropriate, but have clear pragmatic deficiencies. We label our complaints as "Turing Test Triggers" (TTTs) as they indicate where current conversational AI systems fall short compared to human behavior. We develop a taxonomy of pragmatic considerations intended to identify what pragmatic competencies a conversational AI system requires and discuss implications for the design and evaluation of conversational AI systems.

Applications of robotics (such as telepresence, transportation, elder-care, remote health care, cleaning, warehouse logistics, and delivery) are bringing significant changes in individuals' lives and are having profound social impact. Despite the envisioned potential of robotics, the goal of ubiquitous robot assistants augmenting quality of life (and quality of work life) has not yet been realized. Key challenges lie in the complexities of four overarching human-centric objectives that such systems must aim for: 1) improving quality of life of people, especially marginalized communities; 2) anticipating and mitigating unintended negative consequences of technological development; 3) enabling robots to adapt to the desires and needs of human counterparts; 4) respecting the need for human autonomy and agency. Pursuing these objectives requires an integrated cohort of technologists, behavioral scientists and social scientists with a shared vision to pursue a deep, multidisciplinary understanding of how robots interact with individuals and society. We introduce a new term, socially cognizant robotics, to describe this multi-faceted interdisciplinary branch of technology. The emerging practitioner, the socially cognizant roboticist, represents the convergence of socially aware technologists, who can develop intelligent devices that adapt to human and social behavior; and technology-aware social scientists and policymakers, who can translate studies of robotics' social effects into actionable and technically-viable principles and policies. A primary element of socially cognizant robotics is a deliberate "invitation to the table" for social scientists, who bring analytical perspectives and methods that are not typically present in robotics. These perspectives cover two levels of human-technology interaction that we view as essential: the human-robot dyad (Section 2) and the robot-society dyad (Section 3). Figure 1 illustrates how these levels might operate in the context of the workplace and everyday life.

Recent years have seen growing interest in developing and applying perceptual similarity metrics. Research has shown the superiority of perceptual metrics over pixel-wise metrics in aligning with human perception and serving as a proxy for the human visual system. On the other hand, as perceptual metrics rely on neural networks, there is a growing concern regarding their resilience, given the established vulnerability of neural networks to adversarial attacks. It is indeed logical to infer that perceptual metrics may inherit both the strengths and shortcomings of neural networks. In this work, we demonstrate the vulnerability of state-of-the-art perceptual similarity metrics based on an ensemble of ViT-based feature extractors to adversarial attacks. We then propose a framework to train a robust perceptual similarity metric called LipSim (Lipschitz Similarity Metric) with provable guarantees. By leveraging 1-Lipschitz neural networks as the backbone, LipSim provides guarded areas around each data point and certificates for all perturbations within an $\ell_2$ ball. Finally, a comprehensive set of experiments shows the performance of LipSim in terms of natural and certified scores and on the image retrieval application. The code is available at https://github.com/SaraGhazanfari/LipSim.

Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI systems to pose existential risks. This paper reviews the evidence for existential risks from AI via misalignment, where AI systems develop goals misaligned with human values, and power-seeking, where misaligned AIs actively seek power. The review examines empirical findings, conceptual arguments and expert opinion relating to specification gaming, goal misgeneralization, and power-seeking. The current state of the evidence is found to be concerning but inconclusive regarding the existence of extreme forms of misaligned power-seeking. Strong empirical evidence of specification gaming combined with strong conceptual evidence for power-seeking make it difficult to dismiss the possibility of existential risk from misaligned power-seeking. On the other hand, to date there are no public empirical examples of misaligned power-seeking in AI systems, and so arguments that future systems will pose an existential risk remain somewhat speculative. Given the current state of the evidence, it is hard to be extremely confident either that misaligned power-seeking poses a large existential risk, or that it poses no existential risk. The fact that we cannot confidently rule out existential risk from AI via misaligned power-seeking is cause for serious concern.

With the growing popularity of code-mixed data, there is an increasing need for better handling of this type of data, which poses a number of challenges, such as dealing with spelling variations, multiple languages, different scripts, and a lack of resources. Current language models face difficulty in effectively handling code-mixed data as they primarily focus on the semantic representation of words and ignore the auditory phonetic features. This leads to difficulties in handling spelling variations in code-mixed text. In this paper, we propose an effective approach for creating language models for handling code-mixed textual data using auditory information of words from SOUNDEX. Our approach includes a pre-training step based on masked-language-modelling, which includes SOUNDEX representations (SAMLM) and a new method of providing input data to the pre-trained model. Through experimentation on various code-mixed datasets (of different languages) for sentiment, offensive and aggression classification tasks, we establish that our novel language modeling approach (SAMLM) results in improved robustness towards adversarial attacks on code-mixed classification tasks. Additionally, our SAMLM based approach also results in better classification results over the popular baselines for code-mixed tasks. We use the explainability technique, SHAP (SHapley Additive exPlanations) to explain how the auditory features incorporated through SAMLM assist the model to handle the code-mixed text effectively and increase robustness against adversarial attacks \footnote{Source code has been made available on \url{https://github.com/20118/DefenseWithPhonetics}, \url{https://www.iitp.ac.in/~ai-nlp-ml/resources.html\#Phonetics}}.

For knowledge intensive NLP tasks, it has been widely accepted that accessing more information is a contributing factor to improvements in the model's end-to-end performance. However, counter-intuitively, too much context can have a negative impact on the model when evaluated on common question answering (QA) datasets. In this paper, we analyze how passages can have a detrimental effect on retrieve-then-read architectures used in question answering. Our empirical evidence indicates that the current read architecture does not fully leverage the retrieved passages and significantly degrades its performance when using the whole passages compared to utilizing subsets of them. Our findings demonstrate that model accuracy can be improved by 10% on two popular QA datasets by filtering out detrimental passages. Additionally, these outcomes are attained by utilizing existing retrieval methods without further training or data. We further highlight the challenges associated with identifying the detrimental passages. First, even with the correct context, the model can make an incorrect prediction, posing a challenge in determining which passages are most influential. Second, evaluation typically considers lexical matching, which is not robust to variations of correct answers. Despite these limitations, our experimental results underscore the pivotal role of identifying and removing these detrimental passages for the context-efficient retrieve-then-read pipeline. Code and data are available at https://github.com/xfactlab/emnlp2023-damaging-retrieval

Modern language models (LMs) have been successfully employed in source code generation and understanding, leading to a significant increase in research focused on learning-based code intelligence, such as automated bug repair, and test case generation. Despite their great potential, language models for code intelligence (LM4Code) are susceptible to potential pitfalls, which hinder realistic performance and further impact their reliability and applicability in real-world deployment. Such challenges drive the need for a comprehensive understanding - not just identifying these issues but delving into their possible implications and existing solutions to build more reliable language models tailored to code intelligence. Based on a well-defined systematic research approach, we conducted an extensive literature review to uncover the pitfalls inherent in LM4Code. Finally, 67 primary studies from top-tier venues have been identified. After carefully examining these studies, we designed a taxonomy of pitfalls in LM4Code research and conducted a systematic study to summarize the issues, implications, current solutions, and challenges of different pitfalls for LM4Code systems. We developed a comprehensive classification scheme that dissects pitfalls across four crucial aspects: data collection and labeling, system design and learning, performance evaluation, and deployment and maintenance. Through this study, we aim to provide a roadmap for researchers and practitioners, facilitating their understanding and utilization of LM4Code in reliable and trustworthy ways.