We evaluate whether LLMs learn to make human-like preference judgements in strategic scenarios as compared with known empirical results. We show that Solar and Mistral exhibit stable value-based preference consistent with human in the prisoner's dilemma, including stake-size effect, and traveler's dilemma, including penalty-size effect. We establish a relationship between model size, value based preference, and superficiality. Finally, we find that models that tend to be less brittle were trained with sliding window attention. Additionally, we contribute a novel method for constructing preference relations from arbitrary LLMs and support for a hypothesis regarding human behavior in the traveler's dilemma.

In this position paper, we discuss the potential for leveraging LLMs as interactive research tools to facilitate collaboration between human coders and AI to effectively annotate online risk data at scale. Collaborative human-AI labeling is a promising approach to annotating large-scale and complex data for various tasks. Yet, tools and methods to support effective human-AI collaboration for data annotation are under-studied. This gap is pertinent because co-labeling tasks need to support a two-way interactive discussion that can add nuance and context, particularly in the context of online risk, which is highly subjective and contextualized. Therefore, we provide some of the early benefits and challenges of using LLMs-based tools for risk annotation and suggest future directions for the HCI research community to leverage LLMs as research tools to facilitate human-AI collaboration in contextualized online data annotation. Our research interests align very well with the purposes of the LLMs as Research Tools workshop to identify ongoing applications and challenges of using LLMs to work with data in HCI research. We anticipate learning valuable insights from organizers and participants into how LLMs can help reshape the HCI community's methods for working with data.

Auditing of AI systems is a promising way to understand and manage ethical problems and societal risks associated with contemporary AI systems, as well as some anticipated future risks. Efforts to develop standards for auditing Artificial Intelligence (AI) systems have therefore understandably gained momentum. However, we argue that creating auditing standards is not just insufficient, but actively harmful by proliferating unheeded and inconsistent standards, especially in light of the rapid evolution and ethical and safety challenges of AI. Instead, the paper proposes the establishment of an AI Audit Standards Board, responsible for developing and updating auditing methods and standards in line with the evolving nature of AI technologies. Such a body would ensure that auditing practices remain relevant, robust, and responsive to the rapid advancements in AI. The paper argues that such a governance structure would also be helpful for maintaining public trust in AI and for promoting a culture of safety and ethical responsibility within the AI industry. Throughout the paper, we draw parallels with other industries, including safety-critical industries like aviation and nuclear energy, as well as more prosaic ones such as financial accounting and pharmaceuticals. AI auditing should emulate those fields, and extend beyond technical assessments to include ethical considerations and stakeholder engagement, but we explain that this is not enough; emulating other fields' governance mechanisms for these processes, and for audit standards creation, is a necessity. We also emphasize the importance of auditing the entire development process of AI systems, not just the final products...

Large Language Models (LLMs) are capable of transforming natural language domain descriptions into plausibly looking PDDL markup. However, ensuring that actions are consistent within domains still remains a challenging task. In this paper we present a novel concept to significantly improve the quality of LLM-generated PDDL models by performing automated consistency checking during the generation process. Although the proposed consistency checking strategies still can't guarantee absolute correctness of generated models, they can serve as valuable source of feedback reducing the amount of correction efforts expected from a human in the loop. We demonstrate the capabilities of our error detection approach on a number of classical and custom planning domains (logistics, gripper, tyreworld, household, pizza).

This study introduces a novel software tool leveraging large language model (LLM) prompts, designed to automate the generation of academic articles from Python code a significant advancement in the fields of biomedical informatics and computer science. Selected for its widespread adoption and analytical versatility, Python served as a foundational proof of concept; however, the underlying methodology and framework exhibit adaptability across various GitHub repo's underlining the tool's broad applicability (Harper 2024). By mitigating the traditionally time-intensive academic writing process, particularly in synthesizing complex datasets and coding outputs, this approach signifies a monumental leap towards streamlining research dissemination. The development was achieved without reliance on advanced language model agents, ensuring high fidelity in the automated generation of coherent and comprehensive academic content. This exploration not only validates the successful application and efficiency of the software but also projects how future integration of LLM agents which could amplify its capabilities, propelling towards a future where scientific findings are disseminated more swiftly and accessibly.

Conversational prompt-engineering-based large language models (LLMs) have enabled targeted control over the output creation, enhancing versatility, adaptability and adhoc retrieval. From another perspective, digital misinformation has reached alarming levels. The anonymity, availability and reach of social media offer fertile ground for rumours to propagate. This work proposes to leverage the advancement of prompting-dependent LLMs to combat misinformation by extending the research efforts of the RumourEval task on its Twitter dataset. To the end, we employ two prompting-based LLM variants (GPT-3.5-turbo and GPT-4) to extend the two RumourEval subtasks: (1) veracity prediction, and (2) stance classification. For veracity prediction, three classifications schemes are experimented per GPT variant. Each scheme is tested in zero-, one- and few-shot settings. Our best results outperform the precedent ones by a substantial margin. For stance classification, prompting-based-approaches show comparable performance to prior results, with no improvement over finetuning methods. Rumour stance subtask is also extended beyond the original setting to allow multiclass classification. All of the generated predictions for both subtasks are equipped with confidence scores determining their trustworthiness degree according to the LLM, and post-hoc justifications for explainability and interpretability purposes. Our primary aim is AI for social good.

A problem with many current Large Language Model (LLM) driven spoken dialogues is the response time. Some efforts such as Groq address this issue by lightning fast processing of the LLM, but we know from the cognitive psychology literature that in human-to-human dialogue often responses occur prior to the speaker completing their utterance. No amount of delay for LLM processing is acceptable if we wish to maintain human dialogue latencies. In this paper, we discuss methods for understanding an utterance in close to real time and generating a response so that the system can comply with human-level conversational turn delays. This means that the information content of the final part of the speaker's utterance is lost to the LLM. Using the Google NaturalQuestions (NQ) database, our results show GPT-4 can effectively fill in missing context from a dropped word at the end of a question over 60% of the time. We also provide some examples of utterances and the impacts of this information loss on the quality of LLM response in the context of an avatar that is currently under development. These results indicate that a simple classifier could be used to determine whether a question is semantically complete, or requires a filler phrase to allow a response to be generated within human dialogue time constraints.

The task of scientific Natural Language Inference (NLI) involves predicting the semantic relation between two sentences extracted from research articles. This task was recently proposed along with a new dataset called SciNLI derived from papers published in the computational linguistics domain. In this paper, we aim to introduce diversity in the scientific NLI task and present MSciNLI, a dataset containing 132,320 sentence pairs extracted from five new scientific domains. The availability of multiple domains makes it possible to study domain shift for scientific NLI. We establish strong baselines on MSciNLI by fine-tuning Pre-trained Language Models (PLMs) and prompting Large Language Models (LLMs). The highest Macro F1 scores of PLM and LLM baselines are 77.21% and 51.77%, respectively, illustrating that MSciNLI is challenging for both types of models. Furthermore, we show that domain shift degrades the performance of scientific NLI models which demonstrates the diverse characteristics of different domains in our dataset. Finally, we use both scientific NLI datasets in an intermediate task transfer learning setting and show that they can improve the performance of downstream tasks in the scientific domain. We make our dataset and code available on Github.

This paper presents our winning submission to Subtask 2 of SemEval 2024 Task 3 on multimodal emotion cause analysis in conversations. We propose a novel Multimodal Emotion Recognition and Multimodal Emotion Cause Extraction (MER-MCE) framework that integrates text, audio, and visual modalities using specialized emotion encoders. Our approach sets itself apart from top-performing teams by leveraging modality-specific features for enhanced emotion understanding and causality inference. Experimental evaluation demonstrates the advantages of our multimodal approach, with our submission achieving a competitive weighted F1 score of 0.3435, ranking third with a margin of only 0.0339 behind the 1st team and 0.0025 behind the 2nd team. Project: https://github.com/MIPS-COLT/MER-MCE.git

Text-to-Vis is an emerging task in the natural language processing (NLP) area that aims to automatically generate data visualizations from natural language questions (NLQs). Despite their progress, existing text-to-vis models often heavily rely on lexical matching between words in the questions and tokens in data schemas. This overreliance on lexical matching may lead to a diminished level of model robustness against input variations. In this study, we thoroughly examine the robustness of current text-to-vis models, an area that has not previously been explored. In particular, we construct the first robustness dataset nvBench-Rob, which contains diverse lexical and phrasal variations based on the original text-to-vis benchmark nvBench. Then, we found that the performance of existing text-to-vis models on this new dataset dramatically drops, implying that these methods exhibit inadequate robustness overall. Finally, we propose a novel framework based on Retrieval-Augmented Generation (RAG) technique, named GRED, specifically designed to address input perturbations in these two variants. The framework consists of three parts: NLQ-Retrieval Generator, Visualization Query-Retrieval Retuner and Annotation-based Debugger, which are used to tackle the challenges posed by natural language variants, programming style differences and data schema variants, respectively. Extensive experimental evaluations show that, compared to the state-of-the-art model RGVisNet in the Text-to-Vis field, GRED performs better in terms of model robustness, with a 32% increase in accuracy on the proposed nvBench-Rob dataset.