Large Language Models (LLMs) vary in their abilities on a range of tasks. Initiatives such as the $\texttt{Open LLM Leaderboard}$ aim to quantify these differences with several large benchmarks (sets of test items to which an LLM can respond either correctly or incorrectly). However, high correlations within and between benchmark scores suggest that (1) there exists a small set of common underlying abilities that these benchmarks measure, and (2) items tap into redundant information and the benchmarks may thus be considerably compressed. We use data from $n > 5000$ LLMs to identify the most informative items of six benchmarks, ARC, GSM8K, HellaSwag, MMLU, TruthfulQA and WinoGrande (with $d=28,632$ items in total). From them we distill a sparse benchmark, $\texttt{metabench}$, that has less than $3\%$ of the original size of all six benchmarks combined. This new sparse benchmark goes beyond point scores by yielding estimators of the underlying benchmark-specific abilities. We show that these estimators (1) can be used to reconstruct each original $\textit{individual}$ benchmark score with, on average, $1.5\%$ root mean square error (RMSE), (2) reconstruct the original $\textit{total}$ score with $0.8\%$ RMSE, and (3) have a single underlying common factor whose Spearman correlation with the total score is $r = 0.93$.

Accurate nutrition estimation helps people make informed decisions about their dietary choices and is crucial for preventing serious health issues. We present NutriBench, the first publicly available natural language meal description based nutrition benchmark. NutriBench consists of 5,000 human-verified meal descriptions with macro-nutrient labels, including carbohydrates, proteins, fats, and calories. The data is divided into 15 subsets varying in complexity based on the number, servings, and popularity of the food items in the meal and the specificity of serving size descriptions. We conducted an extensive evaluation of seven popular and state-of-the-art Large Language Models (LLMs), including GPT-3.5, Llama-3, and a medical domain-specific model with standard, Chain-of-Thought and Retrieval-Augmented Generation strategies on our benchmark for carbohydrate estimation. We also conducted a human study involving expert and non-expert participants and found that LLMs can provide more accurate and faster predictions over a range of complex queries. We present a thorough analysis and comparison of different LLMs, highlighting the opportunities and challenges of using LLMs for nutrition estimation in real-life scenarios. Our benchmark is publicly available at: https://mehak126.github.io/nutribench.html

Sign language understanding has made significant strides; however, there is still no viable solution for generating sign sequences directly from entire spoken content, e.g., text or speech. In this paper, we propose a unified framework for continuous sign language production, easing communication between sign and non-sign language users. In particular, a sequence diffusion model, utilizing embeddings extracted from text or speech, is crafted to generate sign predictions step by step. Moreover, by creating a joint embedding space for text, audio, and sign, we bind these modalities and leverage the semantic consistency among them to provide informative feedback for the model training. This embedding-consistency learning strategy minimizes the reliance on sign triplets and ensures continuous model refinement, even with a missing audio modality. Experiments on How2Sign and PHOENIX14T datasets demonstrate that our model achieves competitive performance in sign language production.

Modeling contextual information in a search session has drawn more and more attention when understanding complex user intents. Recent methods are all data-driven, i.e., they train different models on large-scale search log data to identify the relevance between search contexts and candidate documents. The common training paradigm is to pair the search context with different candidate documents and train the model to rank the clicked documents higher than the unclicked ones. However, this paradigm neglects the symmetric nature of the relevance between the session context and document, i.e., the clicked documents can also be paired with different search contexts when training. In this work, we propose query-oriented data augmentation to enrich search logs and empower the modeling. We generate supplemental training pairs by altering the most important part of a search context, i.e., the current query, and train our model to rank the generated sequence along with the original sequence. This approach enables models to learn that the relevance of a document may vary as the session context changes, leading to a better understanding of users' search patterns. We develop several strategies to alter the current query, resulting in new training data with varying degrees of difficulty. Through experimentation on two extensive public search logs, we have successfully demonstrated the effectiveness of our model.

With the advancements in human-robot interaction (HRI), robots are now capable of operating in close proximity and engaging in physical interactions with humans (pHRI). Likewise, contact-based pHRI is becoming increasingly common as robots are equipped with a range of sensors to perceive human motions. Despite the presence of surveys exploring various aspects of HRI and pHRI, there is presently a gap in comprehensive studies that collect, organize and relate developments across all aspects of contact-based pHRI. It has become challenging to gain a comprehensive understanding of the current state of the field, thoroughly analyze the aspects that have been covered, and identify areas needing further attention. Hence, the present survey. While it includes key developments in pHRI, a particular focus is placed on contact-based interaction, which has numerous applications in industrial, rehabilitation and medical robotics. Across the literature, a common denominator is the importance to establish a safe, compliant and human intention-oriented interaction. This endeavour encompasses aspects of perception, planning and control, and how they work together to enhance safety and reliability. Notably, the survey highlights the application of data-driven techniques: backed by a growing body of literature demonstrating their effectiveness, approaches like reinforcement learning and learning from demonstration have become key to improving robot perception and decision-making within complex and uncertain pHRI scenarios. As the field is yet in its early stage, these observations may help guide future developments and steer research towards the responsible integration of physically interactive robots into workplaces, public spaces, and elements of private life.

Humans share a wide variety of images related to their personal experiences within conversations via instant messaging tools. However, existing works focus on (1) image-sharing behavior in singular sessions, leading to limited long-term social interaction, and (2) a lack of personalized image-sharing behavior. In this work, we introduce Stark, a large-scale long-term multi-modal conversation dataset that covers a wide range of social personas in a multi-modality format, time intervals, and images. To construct Stark automatically, we propose a novel multi-modal contextualization framework, Mcu, that generates long-term multi-modal dialogue distilled from ChatGPT and our proposed Plan-and-Execute image aligner. Using our Stark, we train a multi-modal conversation model, Ultron 7B, which demonstrates impressive visual imagination ability. Furthermore, we demonstrate the effectiveness of our dataset in human evaluation. We make our source code and dataset publicly available.

The verification of Multi-Agent Systems (MAS) poses a significant challenge. Various approaches and methodologies exist to address this challenge; however, tools that support them are not always readily available. Even when such tools are accessible, they tend to be hard-coded, lacking in compositionality, and challenging to use due to a steep learning curve. In this paper, we introduce a methodology designed for the formal verification of MAS in a modular and versatile manner, along with an initial prototype, that we named VITAMIN. Unlike existing verification methodologies and frameworks for MAS, VITAMIN is constructed for easy extension to accommodate various logics (for specifying the properties to verify) and models (for determining on what to verify such properties).

Evaluating the generalisation capabilities of multimodal models based solely on their performance on out-of-distribution data fails to capture their true robustness. This work introduces a comprehensive evaluation framework that systematically examines the role of instructions and inputs in the generalisation abilities of such models, considering architectural design, input perturbations across language and vision modalities, and increased task complexity. The proposed framework uncovers the resilience of multimodal models to extreme instruction perturbations and their vulnerability to observational changes, raising concerns about overfitting to spurious correlations. By employing this evaluation framework on current Transformer-based multimodal models for robotic manipulation tasks, we uncover limitations and suggest future advancements should focus on architectural and training innovations that better integrate multimodal inputs, enhancing a model's generalisation prowess by prioritising sensitivity to input content over incidental correlations.

Large Language Models (LLMs) have sparked substantial interest and debate concerning their potential emergence of Theory of Mind (ToM) ability. Theory of mind evaluations currently focuses on testing models using machine-generated data or game settings prone to shortcuts and spurious correlations, which lacks evaluation of machine ToM ability in real-world human interaction scenarios. This poses a pressing demand to develop new real-world scenario benchmarks. We introduce NegotiationToM, a new benchmark designed to stress-test machine ToM in real-world negotiation surrounding covered multi-dimensional mental states (i.e., desires, beliefs, and intentions). Our benchmark builds upon the Belief-Desire-Intention (BDI) agent modeling theory and conducts the necessary empirical experiments to evaluate large language models. Our findings demonstrate that NegotiationToM is challenging for state-of-the-art LLMs, as they consistently perform significantly worse than humans, even when employing the chain-of-thought (CoT) method.

Despite the rapid development of large language models (LLMs) for the Korean language, there remains an obvious lack of benchmark datasets that test the requisite Korean cultural and linguistic knowledge. Because many existing Korean benchmark datasets are derived from the English counterparts through translation, they often overlook the different cultural contexts. For the few benchmark datasets that are sourced from Korean data capturing cultural knowledge, only narrow tasks such as bias and hate speech detection are offered. To address this gap, we introduce a benchmark of Cultural and Linguistic Intelligence in Korean (CLIcK), a dataset comprising 1,995 QA pairs. CLIcK sources its data from official Korean exams and textbooks, partitioning the questions into eleven categories under the two main categories of language and culture. For each instance in CLIcK, we provide fine-grained annotation of which cultural and linguistic knowledge is required to answer the question correctly. Using CLIcK, we test 13 language models to assess their performance. Our evaluation uncovers insights into their performances across the categories, as well as the diverse factors affecting their comprehension. CLIcK offers the first large-scale comprehensive Korean-centric analysis of LLMs' proficiency in Korean culture and language.