Enabling robots to autonomously perform hybrid motions in diverse environments can be beneficial for long-horizon tasks such as material handling, household chores, and work assistance. This requires extensive exploitation of intrinsic motion capabilities, extraction of affordances from rich environmental information, and planning of physical interaction behaviors. Despite recent progress has demonstrated impressive humanoid whole-body control abilities, they struggle to achieve versatility and adaptability for new tasks. In this work, we propose HYPERmotion, a framework that learns, selects and plans behaviors based on tasks in different scenarios. We combine reinforcement learning with whole-body optimization to generate motion for 38 actuated joints and create a motion library to store the learned skills. We apply the planning and reasoning features of the large language models (LLMs) to complex loco-manipulation tasks, constructing a hierarchical task graph that comprises a series of primitive behaviors to bridge lower-level execution with higher-level planning. By leveraging the interaction of distilled spatial geometry and 2D observation with a visual language model (VLM) to ground knowledge into a robotic morphology selector to choose appropriate actions in single- or dual-arm, legged or wheeled locomotion. Experiments in simulation and real-world show that learned motions can efficiently adapt to new tasks, demonstrating high autonomy from free-text commands in unstructured scenes. Videos and website: hy-motion.github.io/

Reasoning about time is essential for Large Language Models (LLMs) to understand the world. Previous works focus on solving specific tasks, primarily on time-sensitive question answering. While these methods have proven effective, they cannot generalize to a wider spectrum of temporal reasoning tasks. Therefore, we propose a crucial question: Can we build a universal framework to handle a variety of temporal reasoning tasks? To that end, we systematically study 38 temporal reasoning tasks. Based on the observation that 19 tasks are directly related to mathematics, we first leverage the available mathematical dataset to set a solid foundation for temporal reasoning. However, the in-depth study indicates that focusing solely on mathematical enhancement falls short of addressing pure temporal reasoning tasks. To mitigate this limitation, we propose a simple but effective self-critic temporal optimization method to enhance the model's temporal reasoning capabilities without sacrificing general task abilities. Finally, we develop Timo, a model designed to excel in temporal reasoning at the 7B and 13B scales. Notably, Timo outperforms the counterpart LLMs by 10.0 and 7.6 in average accuracy scores and achieves the new state-of-the-art (SOTA) performance of comparable size. Extensive experiments further validate our framework's effectiveness and its generalization across diverse temporal tasks. The code is available at https://github.com/zhaochen0110/Timo.

Understanding the deep semantics of images is essential in the era dominated by social media. However, current research works primarily on the superficial description of images, revealing a notable deficiency in the systematic investigation of the inherent deep semantics. In this work, we introduce DEEPEVAL, a comprehensive benchmark to assess Large Multimodal Models' (LMMs) capacities of visual deep semantics. DEEPEVAL includes human-annotated dataset and three progressive subtasks: fine-grained description selection, in-depth title matching, and deep semantics understanding. Utilizing DEEPEVAL, we evaluate 9 open-source LMMs and GPT-4V(ision). Our evaluation demonstrates a substantial gap between the deep semantic comprehension capabilities of existing LMMs and humans. For example, GPT-4V is 30% behind humans in understanding deep semantics, even though it achieves human-comparable performance in image description. Further analysis reveals that LMM performance on DEEPEVAL varies according to the specific facets of deep semantics explored, indicating the fundamental challenges remaining in developing LMMs.

Bangla (Bengali) is the fifth most spoken language globally and, yet, the problem of automatic grammar correction in Bangla is still in its nascent stage. This is mostly due to the need for a large corpus of grammatically incorrect sentences, with their corresponding correct counterparts. The present state-of-the-art techniques to curate a corpus for grammatically wrong sentences involve random swapping, insertion and deletion of words. However,these steps may not always generate grammatically wrong sentences in Bangla. In this work, we propose a pragmatic approach to generate grammatically wrong sentences in Bangla. We first categorize the different kinds of errors in Bangla into 5 broad classes and 12 finer classes. We then use these to generate grammatically wrong sentences systematically from a correct sentence. This approach can generate a large number of wrong sentences and can, thus, mitigate the challenge of lacking a large corpus for neural networks. We provide a dataset, Vaiyakarana, consisting of 92,830 grammatically incorrect sentences as well as 18,426 correct sentences. We also collected 619 human-generated sentences from essays written by Bangla native speakers. This helped us to understand errors that are more frequent. We evaluated our corpus against neural models and LLMs and also benchmark it against human evaluators who are native speakers of Bangla. Our analysis shows that native speakers are far more accurate than state-of-the-art models to detect whether the sentence is grammatically correct. Our methodology of generating erroneous sentences can be applied for most other Indian languages as well.

Compute-efficient training of large language models (LLMs) has become an important research problem. In this work, we consider data pruning as a method of data-efficient training of LLMs, where we take a data compression view on data pruning. We argue that the amount of information of a sample, or the achievable compression on its description length, represents its sample importance. The key idea is that, less informative samples are likely to contain redundant information, and thus should be pruned first. We leverage log-likelihood function of trained models as a surrogate to measure information content of samples. Experiments reveal a surprising insight that information-based pruning can enhance the generalization capability of the model, improves upon language modeling and downstream tasks as compared to the model trained on the entire dataset.

The idea of personality in descriptive psychology, traditionally defined through observable behavior, has now been extended to Large Language Models (LLMs) to better understand their behavior. This raises a question: do LLMs exhibit distinct and consistent personality traits, similar to humans? Existing self-assessment personality tests, while applicable, lack the necessary validity and reliability for precise personality measurements. To address this, we introduce TRAIT, a new tool consisting of 8K multi-choice questions designed to assess the personality of LLMs with validity and reliability. TRAIT is built on the psychometrically validated human questionnaire, Big Five Inventory (BFI) and Short Dark Triad (SD-3), enhanced with the ATOMIC10X knowledge graph for testing personality in a variety of real scenarios. TRAIT overcomes the reliability and validity issues when measuring personality of LLM with self-assessment, showing the highest scores across three metrics: refusal rate, prompt sensitivity, and option order sensitivity. It reveals notable insights into personality of LLM: 1) LLMs exhibit distinct and consistent personality, which is highly influenced by their training data (i.e., data used for alignment tuning), and 2) current prompting techniques have limited effectiveness in eliciting certain traits, such as high psychopathy or low conscientiousness, suggesting the need for further research in this direction.

Online Large Language Model (LLM) services such as ChatGPT and Claude 3 have transformed business operations and academic research by effortlessly enabling new opportunities. However, due to data-sharing restrictions, sectors such as healthcare and finance prefer to deploy local LLM applications using costly hardware resources. This scenario requires a balance between the effectiveness advantages of LLMs and significant financial burdens. Additionally, the rapid evolution of models increases the frequency and redundancy of benchmarking efforts. Existing benchmarking toolkits, which typically focus on effectiveness, often overlook economic considerations, making their findings less applicable to practical scenarios. To address these challenges, we introduce CEBench, an open-source toolkit specifically designed for multi-objective benchmarking that focuses on the critical trade-offs between expenditure and effectiveness required for LLM deployments. CEBench allows for easy modifications through configuration files, enabling stakeholders to effectively assess and optimize these trade-offs. This strategic capability supports crucial decision-making processes aimed at maximizing effectiveness while minimizing cost impacts. By streamlining the evaluation process and emphasizing cost-effectiveness, CEBench seeks to facilitate the development of economically viable AI solutions across various industries and research fields. The code and demonstration are available in \url{https://github.com/amademicnoboday12/CEBench}.

Challenges in the automated evaluation of Retrieval-Augmented Generation (RAG) Question-Answering (QA) systems include hallucination problems in domain-specific knowledge and the lack of gold standard benchmarks for company internal tasks. This results in difficulties in evaluating RAG variations, like RAG-Fusion (RAGF), in the context of a product QA task at Infineon Technologies. To solve these problems, we propose a comprehensive evaluation framework, which leverages Large Language Models (LLMs) to generate large datasets of synthetic queries based on real user queries and in-domain documents, uses LLM-as-a-judge to rate retrieved documents and answers, evaluates the quality of answers, and ranks different variants of Retrieval-Augmented Generation (RAG) agents with RAGElo's automated Elo-based competition. LLM-as-a-judge rating of a random sample of synthetic queries shows a moderate, positive correlation with domain expert scoring in relevance, accuracy, completeness, and precision. While RAGF outperformed RAG in Elo score, a significance analysis against expert annotations also shows that RAGF significantly outperforms RAG in completeness, but underperforms in precision. In addition, Infineon's RAGF assistant demonstrated slightly higher performance in document relevance based on MRR@5 scores. We find that RAGElo positively aligns with the preferences of human annotators, though due caution is still required. Finally, RAGF's approach leads to more complete answers based on expert annotations and better answers overall based on RAGElo's evaluation criteria.

Large Language Models (LLMs) exhibit positional bias, struggling to utilize information from the middle or end of long contexts. Our study explores LLMs' long-context reasoning by probing their hidden representations. We find that while LLMs encode the position of target information, they often fail to leverage this in generating accurate responses. This reveals a disconnect between information retrieval and utilization, a "know but don't tell" phenomenon. We further analyze the relationship between extraction time and final accuracy, offering insights into the underlying mechanics of transformer models.

FActScore has gained popularity as a metric to estimate the factuality of long-form texts generated by Large Language Models (LLMs) in English. However, there has not been any work in studying the behavior of FActScore in other languages. This paper studies the limitations of each component in the four-component pipeline of FActScore in the multilingual setting. We introduce a new dataset for FActScore on texts generated by strong multilingual LLMs. Our evaluation shows that LLMs exhibit distinct behaviors in both fact extraction and fact scoring tasks. No LLM produces consistent and reliable FActScore across languages with varying levels of resources. We also find that the knowledge source plays an important role in the quality of the estimated FActScore. Using Wikipedia as the knowledge source may hinder the true FActScore of long-form text due to its limited coverage in medium- and low-resource languages. We also incorporate three mitigations to our knowledge source that ultimately improve FActScore estimation across all languages.