We propose the new problem of choosing which dense retrieval model to use when searching on a new collection for which no labels are available, i.e. in a zero-shot setting. Many dense retrieval models are readily available. Each model however is characterized by very differing search effectiveness -- not just on the test portion of the datasets in which the dense representations have been learned but, importantly, also across different datasets for which data was not used to learn the dense representations. This is because dense retrievers typically require training on a large amount of labeled data to achieve satisfactory search effectiveness in a specific dataset or domain. Moreover, effectiveness gains obtained by dense retrievers on datasets for which they are able to observe labels during training, do not necessarily generalise to datasets that have not been observed during training. This is however a hard problem: through empirical experimentation we show that methods inspired by recent work in unsupervised performance evaluation with the presence of domain shift in the area of computer vision and machine learning are not effective for choosing highly performing dense retrievers in our setup. The availability of reliable methods for the selection of dense retrieval models in zero-shot settings that do not require the collection of labels for evaluation would allow to streamline the widespread adoption of dense retrieval. This is therefore an important new problem we believe the information retrieval community should consider. Implementation of methods, along with raw result files and analysis scripts are made publicly available at https://www.github.com/anonymized.

Can ChatGPT provide evidence to support its answers? Does the evidence it suggests actually exist and does it really support its answer? We investigate these questions using a collection of domain-specific knowledge-based questions, specifically prompting ChatGPT to provide both an answer and supporting evidence in the form of references to external sources. We also investigate how different prompts impact answers and evidence. We find that ChatGPT provides correct or partially correct answers in about half of the cases (50.6% of the times), but its suggested references only exist 14% of the times. We further provide insights on the generated references that reveal common traits among the references that ChatGPT generates, and show how even if a reference provided by the model does exist, this reference often does not support the claims ChatGPT attributes to it. Our findings are important because (1) they are the first systematic analysis of the references created by ChatGPT in its answers; (2) they suggest that the model may leverage good quality information in producing correct answers, but is unable to attribute real evidence to support its answers. Prompts, raw result files and manual analysis are made publicly available.

The driving factors behind the development of large language models (LLMs) with impressive learning capabilities are their colossal model sizes and extensive training datasets. Along with the progress in natural language processing, LLMs have been frequently made accessible to the public to foster deeper investigation and applications. However, when it comes to training datasets for these LLMs, especially the recent state-of-the-art models, they are often not fully disclosed. Creating training data for high-performing LLMs involves extensive cleaning and deduplication to ensure the necessary level of quality. The lack of transparency for training data has thus hampered research on attributing and addressing hallucination and bias issues in LLMs, hindering replication efforts and further advancements in the community. These challenges become even more pronounced in multilingual learning scenarios, where the available multilingual text datasets are often inadequately collected and cleaned. Consequently, there is a lack of open-source and readily usable dataset to effectively train LLMs in multiple languages. To overcome this issue, we present CulturaX, a substantial multilingual dataset with 6.3 trillion tokens in 167 languages, tailored for LLM development. Our dataset undergoes meticulous cleaning and deduplication through a rigorous pipeline of multiple stages to accomplish the best quality for model training, including language identification, URL-based filtering, metric-based cleaning, document refinement, and data deduplication. CulturaX is fully released to the public in HuggingFace to facilitate research and advancements in multilingual LLMs: https://huggingface.co/datasets/uonlp/CulturaX.

As Large Language Models are deployed within Artificial Intelligence systems, that are increasingly integrated with human society, it becomes more important than ever to study their internal structures. Higher level abilities of LLMs such as GPT-3.5 emerge in large part due to informative language representations they induce from raw text data during pre-training on trillions of words. These embeddings exist in vector spaces of several thousand dimensions, and their processing involves mapping between multiple vector spaces, with total number of parameters on the order of trillions. Furthermore, these language representations are induced by gradient optimization, resulting in a black box system that is hard to interpret. In this paper, we take a look at the topological structure of neuronal activity in the "brain" of Chat-GPT's foundation language model, and analyze it with respect to a metric representing the notion of fairness. We develop a novel approach to visualize GPT's moral dimensions. We first compute a fairness metric, inspired by social psychology literature, to identify factors that typically influence fairness assessments in humans, such as legitimacy, need, and responsibility. Subsequently, we summarize the manifold's shape using a lower-dimensional simplicial complex, whose topology is derived from this metric. We color it with a heat map associated with this fairness metric, producing human-readable visualizations of the high-dimensional sentence manifold. Our results show that sentence embeddings based on GPT-3.5 can be decomposed into two submanifolds corresponding to fair and unfair moral judgments. This indicates that GPT-based language models develop a moral dimension within their representation spaces and induce an understanding of fairness during their training process.

Abstract-- We present a reactive base control method that enables high performance mobile manipulation on-the-move in environments with static and dynamic obstacles. Performing manipulation tasks while the mobile base remains in motion can significantly decrease the time required to perform multistep tasks, as well as improve the gracefulness of the robot's motion. Existing approaches to manipulation on-the-move either ignore the obstacle avoidance problem or rely on the execution of planned trajectories, which is not suitable in environments with dynamic objects and obstacles. The presented controller addresses both of these deficiencies and demonstrates robust performance of pick-and-place tasks in dynamic environments. The performance is evaluated on several (a) Real-world manipulation on-the-move with dynamic obstacles. On a real-world task with static obstacles, we outperform an existing method by 48% in terms of total task time.

Embodied agents, in the form of virtual agents or social robots, are rapidly becoming more widespread. In human-human interactions, humans use nonverbal behaviours to convey their attitudes, feelings, and intentions. Therefore, this capability is also required for embodied agents in order to enhance the quality and effectiveness of their interactions with humans. In this paper, we propose a novel framework that can generate sequences of joint angles from the speech text and speech audio utterances. Based on a conditional Generative Adversarial Network (GAN), our proposed neural network model learns the relationships between the co-speech gestures and both semantic and acoustic features from the speech input. In order to train our neural network model, we employ a public dataset containing co-speech gestures with corresponding speech audio utterances, which were captured from a single male native English speaker. The results from both objective and subjective evaluations demonstrate the efficacy of our gesture-generation framework for Robots and Embodied Agents.

Argument mining is to analyze argument structure and extract important argument information from unstructured text. An argument mining system can help people automatically gain causal and logical information behind the text. As argumentative corpus gradually increases, like more people begin to argue and debate on social media, argument mining from them is becoming increasingly critical. However, argument mining is still a big challenge in natural language tasks due to its difficulty, and relative techniques are not mature. For example, research on non-tree argument mining needs to be done more. Most works just focus on extracting tree structure argument information. Moreover, current methods cannot accurately describe and capture argument relations and do not predict their types. In this paper, we propose a novel neural model called AutoAM to solve these problems. We first introduce the argument component attention mechanism in our model. It can capture the relevant information between argument components, so our model can better perform argument mining. Our model is a universal end-to-end framework, which can analyze argument structure without constraints like tree structure and complete three subtasks of argument mining in one model. The experiment results show that our model outperforms the existing works on several metrics in two public datasets.

Software frameworks for behaviour are critical in robotics as they enable the correct and efficient execution of functions. While modern behaviour systems have improved their composability, they do not focus on smooth transitions and often lack functionality. In this work, we present the Director, a novel behaviour framework and algorithm that addresses these problems. It has functionality for soft transitions, multiple implementations of the same action chosen based on conditionals, and strict resource control. This system has shown success in the Humanoid Kid Size 2022/2023 Virtual Season and the Humanoid Kid Size RoboCup 2023 Bordeaux competition.

Detecting firearms and accurately localizing individuals carrying them in images or videos is of paramount importance in security, surveillance, and content customization. However, this task presents significant challenges in complex environments due to clutter and the diverse shapes of firearms. To address this problem, we propose a novel approach that leverages human-firearm interaction information, which provides valuable clues for localizing firearm carriers. Our approach incorporates an attention mechanism that effectively distinguishes humans and firearms from the background by focusing on relevant areas. Additionally, we introduce a saliency-driven locality-preserving constraint to learn essential features while preserving foreground information in the input image. By combining these components, our approach achieves exceptional results on a newly proposed dataset. To handle inputs of varying sizes, we pass paired human-firearm instances with attention masks as channels through a deep network for feature computation, utilizing an adaptive average pooling layer. We extensively evaluate our approach against existing methods in human-object interaction detection and achieve significant results (AP=77.8\%) compared to the baseline approach (AP=63.1\%). This demonstrates the effectiveness of leveraging attention mechanisms and saliency-driven locality preservation for accurate human-firearm interaction detection. Our findings contribute to advancing the fields of security and surveillance, enabling more efficient firearm localization and identification in diverse scenarios.

This work presents a new task of Text Expansion (TE), which aims to insert fine-grained modifiers into proper locations of the plain text to concretize or vivify human writings. Different from existing insertion-based writing assistance tasks, TE requires the model to be more flexible in both locating and generation, and also more cautious in keeping basic semantics. We leverage four complementary approaches to construct a dataset with 12 million automatically generated instances and 2K human-annotated references for both English and Chinese. To facilitate automatic evaluation, we design various metrics from multiple perspectives. In particular, we propose Info-Gain to effectively measure the informativeness of expansions, which is an important quality dimension in TE. On top of a pre-trained text-infilling model, we build both pipelined and joint Locate&Infill models, which demonstrate the superiority over the Text2Text baselines, especially in expansion informativeness. Experiments verify the feasibility of the TE task and point out potential directions for future research toward better automatic text expansion.