Vaccine concerns are an ever-evolving target, and can shift quickly as seen during the COVID-19 pandemic. Identifying longitudinal trends in vaccine concerns and misinformation might inform the healthcare space by helping public health efforts strategically allocate resources or information campaigns. We explore the task of detecting vaccine concerns in online discourse using large language models (LLMs) in a zero-shot setting without the need for expensive training datasets. Since real-time monitoring of online sources requires large-scale inference, we explore cost-accuracy trade-offs of different prompting strategies and offer concrete takeaways that may inform choices in system designs for current applications. An analysis of different prompting strategies reveals that classifying the concerns over multiple passes through the LLM, each consisting a boolean question whether the text mentions a vaccine concern or not, works the best. Our results indicate that GPT-4 can strongly outperform crowdworker accuracy when compared to ground truth annotations provided by experts on the recently introduced VaxConcerns dataset, achieving an overall F1 score of 78.7%.

Large Language Model (LLM) leaderboards based on benchmark rankings are regularly used to guide practitioners in model selection. Often, the published leaderboard rankings are taken at face value - we show this is a (potentially costly) mistake. Under existing leaderboards, the relative performance of LLMs is highly sensitive to (often minute) details. We show that for popular multiple choice question benchmarks (e.g. MMLU) minor perturbations to the benchmark, such as changing the order of choices or the method of answer selection, result in changes in rankings up to 8 positions. We explain this phenomenon by conducting systematic experiments over three broad categories of benchmark perturbations and identifying the sources of this behavior. Our analysis results in several best-practice recommendations, including the advantage of a hybrid scoring method for answer selection. Our study highlights the dangers of relying on simple benchmark evaluations and charts the path for more robust evaluation schemes on the existing benchmarks.

The capability of Large Language Models (LLMs) such as GPT-4 to engage in conversation with humans presents a significant leap in Artificial Intelligence (AI) development that is broadly considered to be disruptive for certain technological areas. A human interacting with an LLM may indeed perceive the LLM as an agent with a personality, to the extent that some have even called them sentient (De Cosmo, 2022). While we, of course, do not subscribe to the notion that LLMs are sentient - nor do we believe it is as yet clear what it means to even ask whether an LLM has a personality - there is still the appearance of agency and personality to the human user interacting with the system. Subjecting an LLM to psychometric tests is thus, in our view, less an assessment of some actual personality that the LLM may or may not have, but rather an assessment of the personality or personalities perceived by the human user. As such, our interest is not only in the actual personality profile(s) resulting from the tests, but also in the question whether the profiles are stable over re-tests and how they vary with different (relevant) parameter settings. At the same time, the results beg the question why the results of the tests are what they are.

State-space models (SSMs) have recently demonstrated competitive performance to transformers at large-scale language modeling benchmarks while achieving linear time and memory complexity as a function of sequence length. Mamba, a recently released SSM model, shows impressive performance in both language modeling and long sequence processing tasks. Simultaneously, mixture-of-expert (MoE) models have shown remarkable performance while significantly reducing the compute and latency costs of inference at the expense of a larger memory footprint. In this paper, we present BlackMamba, a novel architecture that combines the Mamba SSM with MoE to obtain the benefits of both. We demonstrate that BlackMamba performs competitively against both Mamba and transformer baselines, and outperforms in inference and training FLOPs. We fully train and open-source 340M/1.5B and 630M/2.8B BlackMamba models on 300B tokens of a custom dataset. We show that BlackMamba inherits and combines both of the benefits of SSM and MoE architectures, combining linear-complexity generation from SSM with cheap and fast inference from MoE. We release all weights, checkpoints, and inference code open-source. Inference code at: https://github.com/Zyphra/BlackMamba

We introduce \textsc{Pok\'eLLMon}, the first LLM-embodied agent that achieves human-parity performance in tactical battle games, as demonstrated in Pok\'emon battles. The design of \textsc{Pok\'eLLMon} incorporates three key strategies: (i) In-context reinforcement learning that instantly consumes text-based feedback derived from battles to iteratively refine the policy; (ii) Knowledge-augmented generation that retrieves external knowledge to counteract hallucination and enables the agent to act timely and properly; (iii) Consistent action generation to mitigate the \textit{panic switching} phenomenon when the agent faces a powerful opponent and wants to elude the battle. We show that online battles against human demonstrates \textsc{Pok\'eLLMon}'s human-like battle strategies and just-in-time decision making, achieving 49\% of win rate in the Ladder competitions and 56\% of win rate in the invited battles. Our implementation and playable battle logs are available at: \url{https://github.com/git-disl/PokeLLMon}.

Leading models for the text-to-SQL task heavily rely on proprietary Large Language Models (LLMs), posing concerns over data privacy. Closing the performance gap between small open-source models and large proprietary models is crucial to mitigate this reliance. To this end, we introduce a novel two-stage fine-tuning approach that decomposes the task into two simpler tasks. Through comprehensive evaluation on two large cross-domain datasets and two small LLMs, we show that this approach improves execution accuracy by 3 to 7 percent, effectively aligning the performance of open-source models with their proprietary counterparts.

The new paradigm of finetuning-as-a-service introduces a new attack surface for Large Language Models (LLMs): a few harmful data uploaded by users can easily trick the finetuning to produce an alignment-broken model. We conduct an empirical analysis and uncover a \textit{harmful embedding drift} phenomenon, showing a probable cause of the alignment-broken effect. Inspired by our findings, we propose Vaccine, a perturbation-aware alignment technique to mitigate the security risk of users finetuning. The core idea of Vaccine is to produce invariant hidden embeddings by progressively adding crafted perturbation to them in the alignment phase. This enables the embeddings to withstand harmful perturbation from un-sanitized user data in the finetuning phase. Our results on open source mainstream LLMs (e.g., Llama2, Opt, Vicuna) demonstrate that Vaccine can boost the robustness of alignment against harmful prompts induced embedding drift while reserving reasoning ability towards benign prompts. Our code is available at \url{https://github.com/git-disl/Vaccine}.

The advent of foundation models has revolutionized the fields of natural language processing and computer vision, paving the way for their application in autonomous driving (AD). This survey presents a comprehensive review of more than 40 research papers, demonstrating the role of foundation models in enhancing AD. Large language models contribute to planning and simulation in AD, particularly through their proficiency in reasoning, code generation and translation. In parallel, vision foundation models are increasingly adapted for critical tasks such as 3D object detection and tracking, as well as creating realistic driving scenarios for simulation and testing. Multi-modal foundation models, integrating diverse inputs, exhibit exceptional visual understanding and spatial reasoning, crucial for end-to-end AD. This survey not only provides a structured taxonomy, categorizing foundation models based on their modalities and functionalities within the AD domain but also delves into the methods employed in current research. It identifies the gaps between existing foundation models and cutting-edge AD approaches, thereby charting future research directions and proposing a roadmap for bridging these gaps.

Large monolithic generative models trained on massive amounts of data have become an increasingly dominant approach in AI research. In this paper, we argue that we should instead construct large generative systems by composing smaller generative models together. We show how such a compositional generative approach enables us to learn distributions in a more data-efficient manner, enabling generalization to parts of the data distribution unseen at training time. We further show how this enables us to program and construct new generative models for tasks completely unseen at training. Finally, we show that in many cases, we can discover separate compositional components from data.

Negotiation is a crucial ability in human communication. Recently, there has been a resurgent research interest in negotiation dialogue systems, whose goal is to create intelligent agents that can assist people in resolving conflicts or reaching agreements. Although there have been many explorations into negotiation dialogue systems, a systematic review of this task has not been performed to date. We aim to fill this gap by investigating recent studies in the field of negotiation dialogue systems, and covering benchmarks, evaluations and methodologies within the literature. We also discuss potential future directions, including multi-modal, multi-party and cross-cultural negotiation scenarios. Our goal is to provide the community with a systematic overview of negotiation dialogue systems and to inspire future research.