Large Language Models (LLMs) have demonstrated significant potential in performing multiple tasks in multimedia applications, ranging from content generation to interactive entertainment, and artistic creation. However, the diversity of downstream tasks in multitask scenarios presents substantial adaptation challenges for LLMs. While traditional methods often succumb to knowledge confusion on their monolithic dense models, Mixture-of-Experts (MoE) has been emerged as a promising solution with its sparse architecture for effective task decoupling. Inspired by the principles of human cognitive neuroscience, we design a novel framework \texttt{Intuition-MoR1E} that leverages the inherent semantic clustering of instances to mimic the human brain to deal with multitask, offering implicit guidance to router for optimized feature allocation. Moreover, we introduce cutting-edge Rank-1 Experts formulation designed to manage a spectrum of intuitions, demonstrating enhanced parameter efficiency and effectiveness in multitask LLM finetuning. Extensive experiments demonstrate that Intuition-MoR1E achieves superior efficiency and 2.15\% overall accuracy improvement across 14 public datasets against other state-of-the-art baselines.

OpenAI has brought the new GPT-4 Turbo to paid ChatGPT users. The company announced the news on X (formerly Twitter), sharing that its large language model has improved math, logical reasoning, coding and writing skills. In reference to the latter, a response to its initial post states that "when writing with ChatGPT, responses will be more direct, less verbose, and use more conversational language." Notably, in December, Microsoft integrated GPT-4 Turbo with its CoPilot AI chatbot and image generator DALL-E 3. Our new GPT-4 Turbo is now available to paid ChatGPT users. We've improved capabilities in writing, math, logical reasoning, and coding.

Large language model chatbots like those powering ChatGPT can reduce people's beliefs in conspiracy theories by debating with them. And the approach they employ could even teach people better ways of interacting with conspiracy theorists. Although past research suggests that the level of beliefs in conspiracy theories in the population hasn't changed substantially in the US or in six surveyed European countries over about a decade, those who subscribe to such ideas have persistent, dogged faith in those beliefs.…

This paper proposes a test to perform Thematic Analysis (TA) with Large Language Model (LLM) on data which is in a different language than English. While there has been initial promising work on using pre-trained LLMs for TA on data in English, we lack any tests on whether these models can reasonably perform the same analysis with good quality in other language. In this paper a test will be proposed using an open access dataset of semi-structured interviews in Italian. The test shows that a pre-trained model can perform such a TA on the data, also using prompts in Italian. A comparative test shows the model capacity to produce themes which have a good resemblance with those produced independently by human researchers. The main implication of this study is that pre-trained LLMs may thus be suitable to support analysis in multilingual situations, so long as the language is supported by the model used.

Preference based Reinforcement Learning (PbRL) removes the need to hand specify a reward function by learning a reward from preference feedback over policy behaviors. Current approaches to PbRL do not address the credit assignment problem inherent in determining which parts of a behavior most contributed to a preference, which result in data intensive approaches and subpar reward functions. We address such limitations by introducing a credit assignment strategy (Hindsight PRIOR) that uses a world model to approximate state importance within a trajectory and then guides rewards to be proportional to state importance through an auxiliary predicted return redistribution objective. Incorporating state importance into reward learning improves the speed of policy learning, overall policy performance, and reward recovery on both locomotion and manipulation tasks. For example, Hindsight PRIOR recovers on average significantly (p < 0.05) more reward on MetaWorld (20%) and DMC (15%). The performance gains and our ablations demonstrate the benefits even a simple credit assignment strategy can have on reward learning and that state importance in forward dynamics prediction is a strong proxy for a state's contribution to a preference decision. Code repository can be found at https://github.com/apple/ Preference-based reinforcement learning (PbRL) learns a policy from preference feedback removing the need to hand specify a reward function. Compared to other methods that avoid hand-specifying a reward function (e.g. Additionally, PbRL can be deployed as human-in-the-loop allowing guidance to adapt on-the-fly to sub-optimal policies, and has shown to be highly effective for complex tasks where reward specification is not feasible (e.g.

In this paper, we focus on generating a synthetic question answering (QA) dataset using an adapted Translate-Align-Retrieve method. Using this method, we created the largest Serbian QA dataset of more than 87K samples, which we name SQuAD-sr. To acknowledge the script duality in Serbian, we generated both Cyrillic and Latin versions of the dataset. We investigate the dataset quality and use it to fine-tune several pre-trained QA models. Best results were obtained by fine-tuning the BERTi\'c model on our Latin SQuAD-sr dataset, achieving 73.91% Exact Match and 82.97% F1 score on the benchmark XQuAD dataset, which we translated into Serbian for the purpose of evaluation. The results show that our model exceeds zero-shot baselines, but fails to go beyond human performance. We note the advantage of using a monolingual pre-trained model over multilingual, as well as the performance increase gained by using Latin over Cyrillic. By performing additional analysis, we show that questions about numeric values or dates are more likely to be answered correctly than other types of questions. Finally, we conclude that SQuAD-sr is of sufficient quality for fine-tuning a Serbian QA model, in the absence of a manually crafted and annotated dataset.

Effective ontology transfer has been a major goal of recent work on event argument extraction (EAE). Two methods in particular -- question answering (QA) and template infilling (TI) -- have emerged as promising approaches to this problem. However, detailed explorations of these techniques' ability to actually enable this transfer are lacking. In this work, we provide such a study, exploring zero-shot transfer using both techniques on six major EAE datasets at both the sentence and document levels. Further, we challenge the growing reliance on LLMs for zero-shot extraction, showing that vastly smaller models trained on an appropriate source ontology can yield zero-shot performance superior to that of GPT-3.5 or GPT-4.

As spacecraft journey further from Earth with more complex missions, systems of greater autonomy and onboard intelligence are called for. Reducing reliance on human-based mission control becomes increasingly critical if we are to increase our rate of solar-system-wide exploration. Recent work has explored AI-based goal-oriented systems to increase the level of autonomy in mission execution. These systems make use of symbolic reasoning managers to make inferences from the state of a spacecraft and a handcrafted knowledge base, enabling autonomous generation of tasks and re-planning. Such systems have proven to be successful in controlled cases, but they are difficult to implement as they require human-crafted ontological models to allow the spacecraft to understand the world. Reinforcement learning has been applied to train robotic agents to pursue a goal. A new architecture for autonomy is called for. This work explores the application of Large Language Models (LLMs) as the high-level control system of a spacecraft. Using a systems engineering approach, this work presents the design and development of an agentic spacecraft controller by leveraging an LLM as a reasoning engine, to evaluate the utility of such an architecture in achieving higher levels of spacecraft autonomy. A series of deep space mission scenarios simulated within the popular game engine Kerbal Space Program (KSP) are used as case studies to evaluate the implementation against the requirements. It is shown the reasoning and planning abilities of present-day LLMs do not scale well as the complexity of a mission increases, but this can be alleviated with adequate prompting frameworks and strategic selection of the agent's level of authority over the host spacecraft. This research evaluates the potential of LLMs in augmenting autonomous decision-making systems for future robotic space applications.

Large language models (LLMs) has experienced exponential growth, they demonstrate remarkable performance across various tasks. Notwithstanding, contemporary research primarily centers on enhancing the size and quality of pretraining data, still utilizing the next token prediction task on autoregressive transformer model structure. The efficacy of this task in truly facilitating the model's comprehension of code logic remains questionable, we speculate that it still interprets code as mere text, while human emphasizes the underlying logical knowledge. In order to prove it, we introduce a new task, "Logically Equivalent Code Selection," which necessitates the selection of logically equivalent code from a candidate set, given a query code. Our experimental findings indicate that current LLMs underperform in this task, since they understand code by unordered bag of keywords. To ameliorate their performance, we propose an advanced pretraining task, "Next Token Prediction+". This task aims to modify the sentence embedding distribution of the LLM without sacrificing its generative capabilities. Our experimental results reveal that following this pretraining, both Code Llama and StarCoder, the prevalent code domain pretraining models, display significant improvements on our logically equivalent code selection task and the code completion task.

Inference with Multimodal Large Language Models (MLLMs) is slow due to their large-language-model backbone which suffers from memory bandwidth bottleneck and generates tokens auto-regressively. In this paper, we explore the application of speculative decoding to enhance the inference efficiency of MLLMs, specifically the LLaVA 7B model. We show that a language-only model can serve as a good draft model for speculative decoding with LLaVA 7B, bypassing the need for image tokens and their associated processing components from the draft model. Our experiments across three different tasks show that speculative decoding can achieve a memory-bound speedup of up to 2.37$\times$ using a 115M parameter language model that we trained from scratch. Additionally, we introduce a compact LLaVA draft model incorporating an image adapter, which shows marginal performance gains in image captioning while maintaining comparable results in other tasks.