The authors conduct an analysis of CTC trained acoustic models to determine how information related to phonetic categories is preserved in CTC-based models which directly output graphemes. The work follows a long line of research that has analyzed neural network representations to determine how they model phonemic representations, although to the best of my knowledge this has not been done previously for CTC-based end-to-end architectures. The results and analysis presented by the authors is interesting, although there are some concerns I have with the conclusions that the authors draw that I would like to clarify these points. Please see my detailed comments below. In the paper, the authors conclude that (Line 159--164) "... after the 5th recurrent layer accuracy goes down again. One possible explanation to this may be that higher layers in the model are more sensitive to long distance information that is needed for the speech recognition task, whereas the local information which is needed for classifying phones is better captured in lower layers."

Summary: The paper proposes a multivariate stochastic process for modeling time series which incorporates locally varying smoothness in the mean and in the covariance matrix. The process uses latent dictionary functions with nested Gaussian process priors; the dictionary functions are linearly related to the observations through a sparse mapping. The authors outline MCMC and online algorithms for approximate Bayesian inference and assess performances using simulation and processing of financial data. Quality: The paper extends the application of the nested Gaussian process priors in [23] to the multivariate case and employs them for both the mean and covariance. This constitutes a sensible extension, and the authors develop an effective inference algorithm.

Large Language Models (LLMs) are deployed as powerful tools for several natural language processing (NLP) applications. Recent works show that modern LLMs can generate self-explanations (SEs), which elicit their intermediate reasoning steps for explaining their behavior. Self-explanations have seen widespread adoption owing to their conversational and plausible nature. However, there is little to no understanding of their faithfulness. In this work, we discuss the dichotomy between faithfulness and plausibility in SEs generated by LLMs. We argue that while LLMs are adept at generating plausible explanations -- seemingly logical and coherent to human users -- these explanations do not necessarily align with the reasoning processes of the LLMs, raising concerns about their faithfulness. We highlight that the current trend towards increasing the plausibility of explanations, primarily driven by the demand for user-friendly interfaces, may come at the cost of diminishing their faithfulness. We assert that the faithfulness of explanations is critical in LLMs employed for high-stakes decision-making. Moreover, we urge the community to identify the faithfulness requirements of real-world applications and ensure explanations meet those needs. Finally, we propose some directions for future work, emphasizing the need for novel methodologies and frameworks that can enhance the faithfulness of self-explanations without compromising their plausibility, essential for the transparent deployment of LLMs in diverse high-stakes domains.

Abductive reasoning aims to find plausible explanations for an event. This style of reasoning is critical for commonsense tasks where there are often multiple plausible explanations. Existing approaches for abductive reasoning in natural language processing (NLP) often rely on manually generated annotations for supervision; however, such annotations can be subjective and biased. Instead of using direct supervision, this work proposes an approach for abductive commonsense reasoning that exploits the fact that only a subset of explanations is correct for a given context. The method uses posterior regularization to enforce a mutual exclusion constraint, encouraging the model to learn the distinction between fluent explanations and plausible ones. We evaluate our approach on a diverse set of abductive reasoning datasets; experimental results show that our approach outperforms or is comparable to directly applying pretrained language models in a zero-shot manner and other knowledge-augmented zero-shot methods.

Setting proper evaluation objectives for explainable artificial intelligence (XAI) is vital for making XAI algorithms follow human communication norms, support human reasoning processes, and fulfill human needs for AI explanations. In this position paper, we examine the most pervasive human-grounded concept in XAI evaluation, explanation plausibility. Plausibility measures how reasonable the machine explanation is compared to the human explanation. Plausibility has been conventionally formulated as an important evaluation objective for AI explainability tasks. We argue against this idea, and show how optimizing and evaluating XAI for plausibility is sometimes harmful, and always ineffective in achieving model understandability, transparency, and trustworthiness. Specifically, evaluating XAI algorithms for plausibility regularizes the machine explanation to express exactly the same content as human explanation, which deviates from the fundamental motivation for humans to explain: expressing similar or alternative reasoning trajectories while conforming to understandable forms or language. Optimizing XAI for plausibility regardless of the model decision correctness also jeopardizes model trustworthiness, because doing so breaks an important assumption in human-human explanation that plausible explanations typically imply correct decisions, and vice versa; and violating this assumption eventually leads to either undertrust or overtrust of AI models. Instead of being the end goal in XAI evaluation, plausibility can serve as an intermediate computational proxy for the human process of interpreting explanations to optimize the utility of XAI.

In this paper I take an empirical look at the question of whether there are rational memckis of discovery and claim that computer programs provida a laboratory for experimentation on this question Recent work in artificial intelligence or Al. has produced programs capaole of serious intellectual work in science Results from Al,viii be used to show that there exist mechanized procedures for discw.ering