Recent trends are emerging in the use of Large Language Models (LLMs) as autonomous agents that take actions based on the content of the user text prompt. This study explores the use of fine-tuned Large Language Models (LLMs) for autonomous spacecraft control, using the Kerbal Space Program Differential Games suite (KSPDG) as a testing environment. Traditional Reinforcement Learning (RL) approaches face limitations in this domain due to insufficient simulation capabilities and data. By leveraging LLMs, specifically fine-tuning models like GPT-3.5 and LLaMA, we demonstrate how these models can effectively control spacecraft using language-based inputs and outputs. Our approach integrates real-time mission telemetry into textual prompts processed by the LLM, which then generate control actions via an agent. The results open a discussion about the potential of LLMs for space operations beyond their nominal use for text-related tasks. Future work aims to expand this methodology to other space control tasks and evaluate the performance of different LLM families. The code is available at this URL: \texttt{https://github.com/ARCLab-MIT/kspdg}.

While various approaches have recently been studied for bias identification, little is known about how implicit language that does not explicitly convey a viewpoint affects bias amplification in large language models. To examine the severity of bias toward a view, we evaluated the performance of two downstream tasks where the implicit and explicit knowledge of social groups were used. First, we present a stress test evaluation by using a biased model in edge cases of excessive bias scenarios. Then, we evaluate how LLMs calibrate linguistically in response to both implicit and explicit opinions when they are aligned with conflicting viewpoints. Our findings reveal a discrepancy in LLM performance in identifying implicit and explicit opinions, with a general tendency of bias toward explicit opinions of opposing stances. Moreover, the bias-aligned models generate more cautious responses using uncertainty phrases compared to the unaligned (zero-shot) base models. The direct, incautious responses of the unaligned models suggest a need for further refinement of decisiveness by incorporating uncertainty markers to enhance their reliability, especially on socially nuanced topics with high subjectivity.

The increasing parameters and expansive dataset of large language models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have partially addressed this need through an exploration of the pre-training data detection problem, which is an instance of a membership inference attack (MIA). This problem involves determining whether a given piece of text has been used during the pre-training phase of the target LLM. Although existing methods have designed various sophisticated MIA score functions to achieve considerable detection performance in pre-trained LLMs, how to achieve high-confidence detection and how to perform MIA on aligned LLMs remain challenging. In this paper, we propose MIA-Tuner, a novel instruction-based MIA method, which instructs LLMs themselves to serve as a more precise pre-training data detector internally, rather than design an external MIA score function. Furthermore, we design two instruction-based safeguards to respectively mitigate the privacy risks brought by the existing methods and MIA-Tuner. To comprehensively evaluate the most recent state-of-the-art LLMs, we collect a more up-to-date MIA benchmark dataset, named WIKIMIA-24, to replace the widely adopted benchmark WIKIMIA. We conduct extensive experiments across various aligned and unaligned LLMs over the two benchmark datasets. The results demonstrate that MIA-Tuner increases the AUC of MIAs from 0.7 to a significantly high level of 0.9.

We demonstrate that large language models (LLMs) exhibit consistent value orientations despite adopting diverse personas, revealing a persistent inertia in their responses that remains stable across the variety of roles they are prompted to assume. To systematically explore this phenomenon, we introduce the role-play-at-scale methodology, which involves prompting LLMs with randomized, diverse personas and analyzing the macroscopic trend of their responses. Unlike previous works that simply feed these questions to LLMs as if testing human subjects, our role-play-at-scale methodology diagnoses inherent tendencies in a systematic and scalable manner by: (1) prompting the model to act in different random personas and (2) asking the same question multiple times for each random persona. This approach reveals consistent patterns in LLM responses across diverse role-play scenarios, indicating deeply encoded inherent tendencies. Our findings contribute to the discourse on value alignment in foundation models and demonstrate the efficacy of role-play-at-scale as a diagnostic tool for uncovering encoded biases in LLMs.

Millimeter-wave (mmWave) communication is promising for next-generation wireless networks but suffers from significant path loss, requiring extensive antenna arrays and frequent beam training. Traditional deep learning models, such as long short-term memory (LSTM), enhance beam tracking accuracy however are limited by poor robustness and generalization. In this letter, we use large language models (LLMs) to improve the robustness of beam prediction. By converting time series data into text-based representations and employing the Prompt-as-Prefix (PaP) technique for contextual enrichment, our approach unleashes the strength of LLMs for time series forecasting. Simulation results demonstrate that our LLM-based method offers superior robustness and generalization compared to LSTM-based models, showcasing the potential of LLMs in wireless communications.

Knowledge editing has been increasingly adopted to correct the false or outdated knowledge in Large Language Models (LLMs). Meanwhile, one critical but under-explored question is: can knowledge editing be used to inject harm into LLMs? In this paper, we propose to reformulate knowledge editing as a new type of safety threat for LLMs, namely Editing Attack, and conduct a systematic investigation with a newly constructed dataset EditAttack. Specifically, we focus on two typical safety risks of Editing Attack including Misinformation Injection and Bias Injection. For the risk of misinformation injection, we first categorize it into commonsense misinformation injection and long-tail misinformation injection. Then, we find that editing attacks can inject both types of misinformation into LLMs, and the effectiveness is particularly high for commonsense misinformation injection. For the risk of bias injection, we discover that not only can biased sentences be injected into LLMs with high effectiveness, but also one single biased sentence injection can cause a bias increase in general outputs of LLMs, which are even highly irrelevant to the injected sentence, indicating a catastrophic impact on the overall fairness of LLMs. Then, we further illustrate the high stealthiness of editing attacks, measured by their impact on the general knowledge and reasoning capacities of LLMs, and show the hardness of defending editing attacks with empirical evidence. Our discoveries demonstrate the emerging misuse risks of knowledge editing techniques on compromising the safety alignment of LLMs and the feasibility of disseminating misinformation or bias with LLMs as new channels.

LLMs-as-a-judge is a recently popularized method which replaces human judgements in task evaluation (Zheng et al. 2024) with automatic evaluation using LLMs. Due to widespread use of RLHF (Reinforcement Learning from Human Feedback), state-of-the-art LLMs like GPT4 and Llama3 are expected to have strong alignment with human preferences when prompted for a quality judgement, such as the coherence of a text. While this seems beneficial, it is not clear whether the assessments by an LLM-as-a-judge constitute only an evaluation based on the instructions in the prompts, or reflect its preference for high-quality data similar to its fine-tune data. To investigate how much influence prompting the LLMs-as-a-judge has on the alignment of AI judgements to human judgements, we analyze prompts with increasing levels of instructions about the target quality of an evaluation, for several LLMs-as-a-judge. Further, we compare to a prompt-free method using model perplexity as a quality measure instead. We aggregate a taxonomy of quality criteria commonly used across state-of-the-art evaluations with LLMs and provide this as a rigorous benchmark of models as judges. Overall, we show that the LLMs-as-a-judge benefit only little from highly detailed instructions in prompts and that perplexity can sometimes align better with human judgements than prompting, especially on textual quality.

The application of the Multi-modal Large Language Models (MLLMs) in medical clinical scenarios remains underexplored. Previous benchmarks only focus on the capacity of the MLLMs in medical visual question-answering (VQA) or report generation and fail to assess the performance of the MLLMs on complex clinical multi-modal tasks. In this paper, we propose a novel Medical Personalized Multi-modal Consultation (Med-PMC) paradigm to evaluate the clinical capacity of the MLLMs. Med-PMC builds a simulated clinical environment where the MLLMs are required to interact with a patient simulator to complete the multi-modal information-gathering and decision-making task. Specifically, the patient simulator is decorated with personalized actors to simulate diverse patients in real scenarios. We conduct extensive experiments to access 12 types of MLLMs, providing a comprehensive view of the MLLMs' clinical performance. We found that current MLLMs fail to gather multimodal information and show potential bias in the decision-making task when consulted with the personalized patient simulators. Further analysis demonstrates the effectiveness of Med-PMC, showing the potential to guide the development of robust and reliable clinical MLLMs. Code and data are available at https://github.com/LiuHC0428/Med-PMC.

Artisanal and Small-Scale Gold Mining (ASGM) is a low-cost yet highly destructive mining practice, leading to environmental disasters across the world's tropical watersheds. The topic of ASGM spans multiple domains of research and information, including natural and social systems, and knowledge is often atomized across a diversity of media and documents. We therefore introduce a knowledge graph (ASGM-KG) that consolidates and provides crucial information about ASGM practices and their environmental effects. The current version of ASGM-KG consists of 1,899 triples extracted using a large language model (LLM) from documents and reports published by both non-governmental and governmental organizations. These documents were carefully selected by a group of tropical ecologists with expertise in ASGM. This knowledge graph was validated using two methods. First, a small team of ASGM experts reviewed and labeled triples as factual or non-factual. Second, we devised and applied an automated factual reduction framework that relies on a search engine and an LLM for labeling triples. Our framework performs as well as five baselines on a publicly available knowledge graph and achieves over 90 accuracy on our ASGM-KG validated by domain experts. ASGM-KG demonstrates an advancement in knowledge aggregation and representation for complex, interdisciplinary environmental crises such as ASGM.

This paper presents the setup and results of the second edition of the BioLaySumm shared task on the Lay Summarisation of Biomedical Research Articles, hosted at the BioNLP Workshop at ACL 2024. In this task edition, we aim to build on the first edition's success by further increasing research interest in this important task and encouraging participants to explore novel approaches that will help advance the state-of-the-art. Encouragingly, we found research interest in the task to be high, with this edition of the task attracting a total of 53 participating teams, a significant increase in engagement from the previous edition. Overall, our results show that a broad range of innovative approaches were adopted by task participants, with a predictable shift towards the use of Large Language Models (LLMs).