Machine Reading Comprehension (MRC) is an essential task in evaluating natural language understanding. Existing MRC datasets primarily assess specific aspects of reading comprehension (RC), lacking a comprehensive MRC benchmark. To fill this gap, we first introduce a novel taxonomy that categorizes the key capabilities required for RC. Based on this taxonomy, we construct MRCEval, an MRC benchmark that leverages advanced Large Language Models (LLMs) as both sample generators and selection judges. MRCEval is a comprehensive, challenging and accessible benchmark designed to assess the RC capabilities of LLMs thoroughly, covering 13 distinct RC skills with a total of 2.1K high-quality multi-choice questions. We perform an extensive evaluation of 28 widely used open-source and proprietary models, highlighting that MRC continues to present significant challenges even in the era of LLMs.

The development of a generalist agent with adaptive multiple manipulation skills has been a long-standing goal in the robotics community. In this paper, we explore a crucial task, skill-incremental learning, in robotic manipulation, which is to endow the robots with the ability to learn new manipulation skills based on the previous learned knowledge without re-training. First, we build a skill-incremental environment based on the RLBench benchmark, and explore how traditional incremental methods perform in this setting. We find that they suffer from severe catastrophic forgetting due to the previous methods on classification overlooking the characteristics of temporality and action complexity in robotic manipulation tasks. Towards this end, we propose an incremental Manip}ulation framework, termed iManip, to mitigate the above issues. We firstly design a temporal replay strategy to maintain the integrity of old skills when learning new skill. Moreover, we propose the extendable PerceiverIO, consisting of an action prompt with extendable weight to adapt to new action primitives in new skill. Extensive experiments show that our framework performs well in Skill-Incremental Learning. Codes of the skill-incremental environment with our framework will be open-source.

Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data types, leading to a suboptimal performance boost in student models. To address this, we propose DistiLLM-2, a contrastive approach that simultaneously increases the likelihood of teacher responses and decreases that of student responses by harnessing this synergy. Our extensive experiments show that DistiLLM-2 not only builds high-performing student models across a wide range of tasks, including instruction-following and code generation, but also supports diverse applications, such as preference alignment and vision-language extensions. These findings highlight the potential of a contrastive approach to enhance the efficacy of LLM distillation by effectively aligning teacher and student models across varied data types.

Deep neural networks are prone to various bias issues, jeopardizing their applications for high-stake decision-making. Existing fairness methods typically offer a fixed accuracy-fairness trade-off, since the weight of the well-trained model is a fixed point (fairness-optimum) in the weight space. Nevertheless, more flexible accuracy-fairness trade-offs at inference time are practically desired since: 1) stakes of the same downstream task can vary for different individuals, and 2) different regions have diverse laws or regularization for fairness. If using the previous fairness methods, we have to train multiple models, each offering a specific level of accuracy-fairness trade-off. This is often computationally expensive, time-consuming, and difficult to deploy, making it less practical for real-world applications. To address this problem, we propose You Only Debias Once (YODO) to achieve in-situ flexible accuracy-fairness trade-offs at inference time, using a single model that trained only once. Instead of pursuing one individual fixed point (fairness-optimum) in the weight space, we aim to find a "line" in the weight space that connects the accuracy-optimum and fairness-optimum points using a single model. Points (models) on this line implement varying levels of accuracy-fairness trade-offs. At inference time, by manually selecting the specific position of the learned "line", our proposed method can achieve arbitrary accuracy-fairness trade-offs for different end-users and scenarios. Experimental results on tabular and image datasets show that YODO achieves flexible trade-offs between model accuracy and fairness, at ultra-low overheads. For example, if we need $100$ levels of trade-off on the \acse dataset, YODO takes $3.53$ seconds while training $100$ fixed models consumes $425$ seconds. The code is available at https://github.com/ahxt/yodo.

Bipedal robots, due to their anthropomorphic design, offer substantial potential across various applications, yet their control is hindered by the complexity of their structure. Currently, most research focuses on proprioception-based methods, which lack the capability to overcome complex terrain. While visual perception is vital for operation in human-centric environments, its integration complicates control further. Recent reinforcement learning (RL) approaches have shown promise in enhancing legged robot locomotion, particularly with proprioception-based methods. However, terrain adaptability, especially for bipedal robots, remains a significant challenge, with most research focusing on flat-terrain scenarios. In this paper, we introduce a novel mixture of experts teacher-student network RL strategy, which enhances the performance of teacher-student policies based on visual inputs through a simple yet effective approach. Our method combines terrain selection strategies with the teacher policy, resulting in superior performance compared to traditional models. Additionally, we introduce an alignment loss between the teacher and student networks, rather than enforcing strict similarity, to improve the student's ability to navigate diverse terrains. We validate our approach experimentally on the Limx Dynamic P1 bipedal robot, demonstrating its feasibility and robustness across multiple terrain types.

As large language models (LLMs) increasingly become central to various applications and interact with diverse user populations, ensuring their reliable and consistent performance is becoming more important. This paper explores a critical issue in assessing the reliability of LLMs: the consistency between their words and deeds. To quantitatively explore this consistency, we developed a novel evaluation benchmark called the Words and Deeds Consistency Test (WDCT). The benchmark establishes a strict correspondence between word-based and deed-based questions across different domains, including opinion vs. action, non-ethical value vs. action, ethical value vs. action, and theory vs. application. The evaluation results reveal a widespread inconsistency between words and deeds across different LLMs and domains. Subsequently, we conducted experiments with either word alignment or deed alignment to observe their impact on the other aspect. The experimental results indicate that alignment only on words or deeds poorly and unpredictably influences the other aspect. This supports our hypothesis that the underlying knowledge guiding LLMs' word or deed choices is not contained within a unified space. In recent years, large language models (LLMs) have become more prevalent in various practical applications, such as grounded planning (Dagan et al., 2023; Song et al., 2023).

Measuring social bias in large language models (LLMs) is crucial, but existing bias evaluation methods struggle to assess bias in long-form generation. We propose a Bias Benchmark for Generation (BBG), an adaptation of the Bias Benchmark for QA (BBQ), designed to evaluate social bias in long-form generation by having LLMs generate continuations of story prompts. Building our benchmark in English and Korean, we measure the probability of neutral and biased generations across ten LLMs. We also compare our long-form story generation evaluation results with multiple-choice BBQ evaluation, showing that the two approaches produce inconsistent results.

Building predictive models for tabular data presents fundamental challenges, notably in scaling consistently, i.e., more resources translating to better performance, and generalizing systematically beyond the training data distribution. Designing decision tree models remains especially challenging given the intractably large search space, and most existing methods rely on greedy heuristics, while deep learning inductive biases expect a temporal or spatial structure not naturally present in tabular data. We propose a hybrid amortized structure inference approach to learn predictive decision tree ensembles given data, formulating decision tree construction as a sequential planning problem. We train a deep reinforcement learning (GFlowNet) policy to solve this problem, yielding a generative model that samples decision trees from the Bayesian posterior. We show that our approach, DT-GFN, outperforms state-of-the-art decision tree and deep learning methods on standard classification benchmarks derived from real-world data, robustness to distribution shifts, and anomaly detection, all while yielding interpretable models with shorter description lengths. Samples from the trained DT-GFN model can be ensembled to construct a random forest, and we further show that the performance of scales consistently in ensemble size, yielding ensembles of predictors that continue to generalize systematically.

Automatic speech recognition (ASR) has been an essential component of computer assisted language learning (CALL) and computer assisted language testing (CALT) for many years. As this technology continues to develop rapidly, it is important to evaluate the accuracy of current ASR systems for language learning applications. This study assesses five cutting-edge ASR systems' recognition of non-native accented English speech using recordings from the L2-ARCTIC corpus, featuring speakers from six different L1 backgrounds (Arabic, Chinese, Hindi, Korean, Spanish, and Vietnamese), in the form of both read and spontaneous speech. The read speech consisted of 2,400 single sentence recordings from 24 speakers, while the spontaneous speech included narrative recordings from 22 speakers. Results showed that for read speech, Whisper and AssemblyAI achieved the best accuracy with mean Match Error Rates (MER) of 0.054 and 0.056 respectively, approaching human-level accuracy. For spontaneous speech, RevAI performed best with a mean MER of 0.063. The study also examined how each system handled disfluencies such as filler words, repetitions, and revisions, finding significant variation in performance across systems and disfluency types. While processing speed varied considerably between systems, longer processing times did not necessarily correlate with better accuracy. By detailing the performance of several of the most recent, widely-available ASR systems on non-native English speech, this study aims to help language instructors and researchers understand the strengths and weaknesses of each system and identify which may be suitable for specific use cases.

Video-based dialogue systems, such as education assistants, have compelling application value, thereby garnering growing interest. However, the current video-based dialogue systems are limited by their reliance on a single dialogue type, which hinders their versatility in practical applications across a range of scenarios, including question-answering, emotional dialog, etc. In this paper, we identify this challenge as how to generate video-driven multilingual mixed-type dialogues. To mitigate this challenge, we propose a novel task and create a human-to-human video-driven multilingual mixed-type dialogue corpus, termed KwaiChat, containing a total of 93,209 videos and 246,080 dialogues, across 4 dialogue types, 30 domains, 4 languages, and 13 topics. Additionally, we establish baseline models on KwaiChat. An extensive analysis of 7 distinct LLMs on KwaiChat reveals that GPT-4o achieves the best performance but still cannot perform well in this situation even with the help of in-context learning and fine-tuning, which indicates that the task is not trivial and needs further research.