Large language models (LLMs) are currently being used to answer medical questions across a variety of clinical domains. Recent top-performing commercial LLMs, in particular, are also capable of citing sources to support their responses. In this paper, we ask: do the sources that LLMs generate actually support the claims that they make? To answer this, we propose three contributions. First, as expert medical annotations are an expensive and time-consuming bottleneck for scalable evaluation, we demonstrate that GPT-4 is highly accurate in validating source relevance, agreeing 88% of the time with a panel of medical doctors. Second, we develop an end-to-end, automated pipeline called \textit{SourceCheckup} and use it to evaluate five top-performing LLMs on a dataset of 1200 generated questions, totaling over 40K pairs of statements and sources. Interestingly, we find that between ~50% to 90% of LLM responses are not fully supported by the sources they provide. We also evaluate GPT-4 with retrieval augmented generation (RAG) and find that, even still, around 30\% of individual statements are unsupported, while nearly half of its responses are not fully supported. Third, we open-source our curated dataset of medical questions and expert annotations for future evaluations. Given the rapid pace of LLM development and the potential harms of incorrect or outdated medical information, it is crucial to also understand and quantify their capability to produce relevant, trustworthy medical references.

Prescriptive AI represents a transformative shift in decision-making, offering causal insights and actionable recommendations. Despite its huge potential, enterprise adoption often faces several challenges. The first challenge is caused by the limitations of observational data for accurate causal inference which is typically a prerequisite for good decision-making. The second pertains to the interpretability of recommendations, which is crucial for enterprise decision-making settings. The third challenge is the silos between data scientists and business users, hindering effective collaboration. This paper outlines an initiative from IBM Research, aiming to address some of these challenges by offering a suite of prescriptive AI solutions. Leveraging insights from various research papers, the solution suite includes scalable causal inference methods, interpretable decision-making approaches, and the integration of large language models (LLMs) to bridge communication gaps via a conversation agent. A proof-of-concept, PresAIse, demonstrates the solutions' potential by enabling non-ML experts to interact with prescriptive AI models via a natural language interface, democratizing advanced analytics for strategic decision-making.

The emergence of large language models (LLMs), and their increased use in user-facing systems, has led to substantial privacy concerns. To date, research on these privacy concerns has been model-centered: exploring how LLMs lead to privacy risks like memorization, or can be used to infer personal characteristics about people from their content. We argue that there is a need for more research focusing on the human aspect of these privacy issues: e.g., research on how design paradigms for LLMs affect users' disclosure behaviors, users' mental models and preferences for privacy controls, and the design of tools, systems, and artifacts that empower end-users to reclaim ownership over their personal data. To build usable, efficient, and privacy-friendly systems powered by these models with imperfect privacy properties, our goal is to initiate discussions to outline an agenda for conducting human-centered research on privacy issues in LLM-powered systems. This Special Interest Group (SIG) aims to bring together researchers with backgrounds in usable security and privacy, human-AI collaboration, NLP, or any other related domains to share their perspectives and experiences on this problem, to help our community establish a collective understanding of the challenges, research opportunities, research methods, and strategies to collaborate with researchers outside of HCI.

Large language models (LLMs) have shown remarkable advances in language generation and understanding but are also prone to exhibiting harmful social biases. While recognition of these behaviors has generated an abundance of bias mitigation techniques, most require modifications to the training data, model parameters, or decoding strategy, which may be infeasible without access to a trainable model. In this work, we leverage the zero-shot capabilities of LLMs to reduce stereotyping in a technique we introduce as zero-shot self-debiasing. With two approaches, self-debiasing via explanation and self-debiasing via reprompting, we show that self-debiasing can significantly reduce the degree of stereotyping across nine different social groups while relying only on the LLM itself and a simple prompt, with explanations correctly identifying invalid assumptions and reprompting delivering the greatest reductions in bias. We hope this work opens inquiry into other zero-shot techniques for bias mitigation.

Social science NLP tasks, such as emotion or humor detection, are required to capture the semantics along with the implicit pragmatics from text, often with limited amounts of training data. Instruction tuning has been shown to improve the many capabilities of large language models (LLMs) such as commonsense reasoning, reading comprehension, and computer programming. However, little is known about the effectiveness of instruction tuning on the social domain where implicit pragmatic cues are often needed to be captured. We explore the use of instruction tuning for social science NLP tasks and introduce Socialite-Llama -- an open-source, instruction-tuned Llama. On a suite of 20 social science tasks, Socialite-Llama improves upon the performance of Llama as well as matches or improves upon the performance of a state-of-the-art, multi-task finetuned model on a majority of them. Further, Socialite-Llama also leads to improvement on 5 out of 6 related social tasks as compared to Llama, suggesting instruction tuning can lead to generalized social understanding. All resources including our code, model and dataset can be found through bit.ly/socialitellama.

The task of identifying public opinions on social media, particularly regarding climate activism and the detection of hate events, has emerged as a critical area of research in our rapidly changing world. With a growing number of people voicing either to support or oppose to climate-related issues - understanding these diverse viewpoints has become increasingly vital. Our team, MasonPerplexity, participates in a significant research initiative focused on this subject. We extensively test various models and methods, discovering that our most effective results are achieved through ensemble modeling, enhanced by data augmentation techniques like back-translation. In the specific components of this research task, our team achieved notable positions, ranking 5th, 1st, and 6th in the respective sub-tasks, thereby illustrating the effectiveness of our approach in this important field of study.

The automatic identification of offensive language such as hate speech is important to keep discussions civil in online communities. Identifying hate speech in multimodal content is a particularly challenging task because offensiveness can be manifested in either words or images or a juxtaposition of the two. This paper presents the MasonPerplexity submission for the Shared Task on Multimodal Hate Speech Event Detection at CASE 2024 at EACL 2024. The task is divided into two sub-tasks: sub-task A focuses on the identification of hate speech and sub-task B focuses on the identification of targets in text-embedded images during political events. We use an XLM-roBERTa-large model for sub-task A and an ensemble approach combining XLM-roBERTa-base, BERTweet-large, and BERT-base for sub-task B. Our approach obtained 0.8347 F1-score in sub-task A and 0.6741 F1-score in sub-task B ranking 3rd on both sub-tasks.

Recent studies have shown that code language models at scale demonstrate significant performance gains on downstream tasks, i.e., code generation. However, most of the existing works on code representation learning train models at a hundred million parameter scale using very limited pretraining corpora. In this work, we fuel code representation learning with a vast amount of code data via a two-stage pretraining scheme. We first train the encoders via a mix that leverages both randomness in masking language modeling and the structure aspect of programming language. We then enhance the representations via contrastive learning with hard negative and hard positive constructed in an unsupervised manner. We establish an off-the-shelf encoder model that persistently outperforms the existing models on a wide variety of downstream tasks by large margins. To comprehend the factors contributing to successful code representation learning, we conduct detailed ablations and share our findings on (i) a customized and effective token-level denoising scheme for source code; (ii) the importance of hard negatives and hard positives; (iii) how the proposed bimodal contrastive learning boost the cross-lingual semantic search performance; and (iv) how the pretraining schemes decide the downstream task performance scales with the model size.

This article introduces NB-Whisper, an adaptation of OpenAI's Whisper, specifically fine-tuned for Norwegian language Automatic Speech Recognition (ASR). We highlight its key contributions and summarise the results achieved in converting spoken Norwegian into written forms and translating other languages into Norwegian. We show that we are able to improve the Norwegian Bokm{\aa}l transcription by OpenAI Whisper Large-v3 from a WER of 10.4 to 6.6 on the Fleurs Dataset and from 6.8 to 2.2 on the NST dataset.

Large foundation models (LFMs) are claiming incredible performances. Yet great concerns have been raised about their mythic and uninterpreted potentials not only in machine learning, but also in various other disciplines. In this position paper, we propose to identify a neglected issue deeply rooted in LFMs: Catastrophic Inheritance, describing the weaknesses and limitations inherited from biased large-scale pre-training data to behaviors of LFMs on the downstream tasks, including samples that are corrupted, long-tailed, noisy, out-of-distributed, to name a few. Such inheritance can potentially cause catastrophes to downstream applications, such as bias, lack of generalization, deteriorated performance, security vulnerability, privacy leakage, and value misalignment. We discuss the challenges behind this issue and propose UIM, a framework to Understand the catastrophic inheritance of LFMs from both pre-training and downstream adaptation, Interpret the implications of catastrophic inheritance on downstream tasks, and how to Mitigate it. UIM aims to unite both the machine learning and social sciences communities for more responsible and promising AI development and deployment.