Retrieval-Augmented Language Models boost task performance, owing to the retriever that provides external knowledge. Although crucial, the retriever primarily focuses on semantics relevance, which may not always be effective for generation. Thus, utility-based retrieval has emerged as a promising topic, prioritizing passages that provides valid benefits for downstream tasks. However, due to insufficient understanding, capturing passage utility accurately remains unexplored. This work proposes SCARLet, a framework for training utility-based retrievers in RALMs, which incorporates two key factors, multi-task generalization and inter-passage interaction. First, SCARLet constructs shared context on which training data for various tasks is synthesized. This mitigates semantic bias from context differences, allowing retrievers to focus on learning task-specific utility for better task generalization. Next, SCARLet uses a perturbation-based attribution method to estimate passage-level utility for shared context, which reflects interactions between passages and provides more accurate feedback. We evaluate our approach on ten datasets across various tasks, both in-domain and out-of-domain, showing that retrievers trained by SCARLet consistently improve the overall performance of RALMs.

Scaling test-time compute has emerged as a key strategy for enhancing the reasoning capabilities of large language models (LLMs), particularly in tasks like mathematical problem-solving. A traditional approach, Self-Consistency (SC), generates multiple solutions to a problem and selects the most common answer via majority voting. Another common method involves scoring each solution with a reward model (verifier) and choosing the best one. Recent advancements in Generative Reward Models (GenRM) reframe verification as a next-token prediction task, enabling inference-time scaling along a new axis. Specifically, GenRM generates multiple verification chains-of-thought to score each solution. Under a limited inference budget, this introduces a fundamental trade-off: should you spend the budget on scaling solutions via SC or generate fewer solutions and allocate compute to verification via GenRM? To address this, we evaluate GenRM against SC under a fixed inference budget. Interestingly, we find that SC is more compute-efficient than GenRM for most practical inference budgets across diverse models and datasets. For instance, GenRM first matches SC after consuming up to 8x the inference compute and requires significantly more compute to outperform it. Furthermore, we derive inference scaling laws for the GenRM paradigm, revealing that compute-optimal inference favors scaling solution generation more aggressively than scaling the number of verifications. Our work provides practical guidance on optimizing test-time scaling by balancing solution generation and verification. The code is available at https://github.com/nishadsinghi/sc-genrm-scaling.

Chinese Grammatical Error Correction (CGEC) is a critical task in Natural Language Processing, addressing the growing demand for automated writing assistance in both second-language (L2) and native (L1) Chinese writing. While L2 learners struggle with mastering complex grammatical structures, L1 users also benefit from CGEC in academic, professional, and formal contexts where writing precision is essential. This survey provides a comprehensive review of CGEC research, covering datasets, annotation schemes, evaluation methodologies, and system advancements. We examine widely used CGEC datasets, highlighting their characteristics, limitations, and the need for improved standardization. We also analyze error annotation frameworks, discussing challenges such as word segmentation ambiguity and the classification of Chinese-specific error types. Furthermore, we review evaluation metrics, focusing on their adaptation from English GEC to Chinese, including character-level scoring and the use of multiple references. In terms of system development, we trace the evolution from rule-based and statistical approaches to neural architectures, including Transformer-based models and the integration of large pre-trained language models. By consolidating existing research and identifying key challenges, this survey provides insights into the current state of CGEC and outlines future directions, including refining annotation standards to address segmentation challenges, and leveraging multilingual approaches to enhance CGEC.

Electronic dictionaries have largely replaced paper dictionaries and become central tools for L2 learners seeking to expand their vocabulary. Users often assume these resources are reliable and rarely question the validity of the definitions provided. The accuracy of major E-dictionaries is seldom scrutinized, and little attention has been paid to how their corpora are constructed. Research on dictionary use, particularly the limitations of electronic dictionaries, remains scarce. This study adopts a combined method of experimentation, user survey, and dictionary critique to examine Youdao, one of the most widely used E-dictionaries in China. The experiment involved a translation task paired with retrospective reflection. Participants were asked to translate sentences containing words that are insufficiently or inaccurately defined in Youdao. Their consultation behavior was recorded to analyze how faulty definitions influenced comprehension. Results show that incomplete or misleading definitions can cause serious misunderstandings. Additionally, students exhibited problematic consultation habits. The study further explores how such flawed definitions originate, highlighting issues in data processing and the integration of AI and machine learning technologies in dictionary construction. The findings suggest a need for better training in dictionary literacy for users, as well as improvements in the underlying AI models used to build E-dictionaries.

As language models improve and become capable of performing more complex tasks across modalities, evaluating them automatically becomes increasingly challenging. Developing strong and robust task-specific automatic metrics gets harder, and human-annotated test sets -- which are expensive to create -- saturate more quickly. A compelling alternative is to design reliable strategies to automate the creation of test data and evaluation, but previous attempts either rely on pre-existing data, or focus solely on individual tasks. We present Zero-shot Benchmarking (ZSB), a framework for creating high-quality benchmarks for any task by leveraging language models for both synthetic test data creation and evaluation. ZSB is simple and flexible: it requires only the creation of a prompt for data generation and one for evaluation; it is scalable to tasks and languages where collecting real-world data is costly or impractical; it is model-agnostic, allowing the creation of increasingly challenging benchmarks as models improve. To assess the effectiveness of our framework, we create benchmarks for five text-only tasks and a multi-modal one: general capabilities in four languages (English, Chinese, French, and Korean), translation, and general vision-language capabilities in English. We then rank a broad range of open and closed systems on our benchmarks. ZSB rankings consistently correlate strongly with human rankings, outperforming widely-adopted standard benchmarks. Through ablations, we find that strong benchmarks can be created with open models, and that judge model size and dataset variety are crucial drivers of performance. We release all our benchmarks, and code to reproduce our experiments and to produce new benchmarks.

Since safe control of ego-vehicles depends on accurately predicting the future states of surrounding dynamic agents, numerous motion forecasting models [1, 2] have been developed to forecast an agent's future motions from historical data. Nevertheless, these predictions remain inherently prone to error, primarily because they lack information about hidden contexts or intents--such as agents' goals, velocity preferences, or even social relationships among human agents. To address these limitations, conformal prediction (CP) [3, 4] has been employed to reliably assess the models' predictive capabilities. The method offers a principled yet straightforward procedure for calibrating the models. At test time, the calibration results can be used to construct a confidence set that contains the true future states of the environment, assuming that the test and calibration data are exchangeable (i.e., their joint distribution is symmetric). Consequently, CP has been successfully applied to a variety of problems, including reinforcement learning [5, 6], linear This work was supported in part by the Information and Communications Technology Planning and Evaluation (IITP) grants funded by MSIT No. 2022-0-00124, No. 2022-0-00480 and No. RS-2021-II211343, Artificial Intelligence Graduate School Program (Seoul National University). The authors are with the Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul 08826, South Korea,{sju5379, jungbbal, insoonyang }@snu.ac.kr arXiv:2504.00447v1

Despite numerous efforts to mitigate their biases, ML systems continue to harm already-marginalized people. While predominant ML approaches assume bias can be removed and fair models can be created, we show that these are not always possible, nor desirable, goals. We reframe the problem of ML bias by creating models to identify biased language, drawing attention to a dataset's biases rather than trying to remove them. Then, through a workshop, we evaluated the models for a specific use case: workflows of information and heritage professionals. Our findings demonstrate the limitations of ML for identifying bias due to its contextual nature, the way in which approaches to mitigating it can simultaneously privilege and oppress different communities, and its inevitability. We demonstrate the need to expand ML approaches to bias and fairness, providing a mixed-methods approach to investigating the feasibility of removing bias or achieving fairness in a given ML use case.

Humans can continuously acquire new skills and knowledge by exploiting existing ones for improved learning, without forgetting them. Similarly, 'continual learning' in machine learning aims to learn new information while preserving the previously acquired knowledge. Existing research often overlooks the nature of human learning, where tasks are interleaved due to human choice or environmental constraints. So, almost never do humans master one task before switching to the next. To investigate to what extent human-like learning can benefit the learner, we propose a method that interleaves tasks based on their 'learning progress' and energy consumption. From a machine learning perspective, our approach can be seen as a multi-task learning system that balances learning performance with energy constraints while mimicking ecologically realistic human task learning. To assess the validity of our approach, we consider a robot learning setting in simulation, where the robot learns the effect of its actions in different contexts. The conducted experiments show that our proposed method achieves better performance than sequential task learning and reduces energy consumption for learning the tasks.

All the images in this paper are best viewed in color on a computer screen at 200% zoom. Abstract -- Autonomous aerial robots are becoming commonplace in our lives. Hands-on aerial robotics courses are pivotal in training the next-generation workforce to meet the growing market demands. Such an efficient and compelling course depends on a reliable testbed. We utilize pose from an external localization system to hallucinate real-time and photorealistic visual sensors using 3D Gaussian Splatting. This enables stress-free testing of autonomy algorithms on aerial robots without the risk of crashing into obstacles. We achieve over 100Hz of system update rate. Lastly, we build upon our past experiences of offering hands-on aerial robotics courses and propose a new open-source and open-hardware curriculum based on VizFlyt for the future. We test our framework on various course projects in real-world HITL experiments and present the results showing the efficacy of such a system and its large potential use cases. Code, datasets, hardware guides and demo videos are available at https://pear .wpi.edu/research/vizflyt.html

Large Language models (LLMs) have been prominent for language translation, including low-resource languages. There has been limited study about the assessment of the quality of translations generated by LLMs, including Gemini, GPT and Google Translate. In this study, we address this limitation by using semantic and sentiment analysis of selected LLMs for Indian languages, including Sanskrit, Telugu and Hindi. We select prominent texts that have been well translated by experts and use LLMs to generate their translations to English, and then we provide a comparison with selected expert (human) translations. Our findings suggest that while LLMs have made significant progress in translation accuracy, challenges remain in preserving sentiment and semantic integrity, especially in figurative and philosophical contexts. The sentiment analysis revealed that GPT-4o and GPT-3.5 are better at preserving the sentiments for the Bhagavad Gita (Sanskrit-English) translations when compared to Google Translate. We observed a similar trend for the case of Tamas (Hindi-English) and Maha P (Telugu-English) translations. GPT-4o performs similarly to GPT-3.5 in the translation in terms of sentiments for the three languages. We found that LLMs are generally better at translation for capturing sentiments when compared to Google Translate.