The emergence of multimodal LLM-based agents (MLAs) has transformed interaction paradigms by seamlessly integrating vision, language, action and dynamic environments, enabling unprecedented autonomous capabilities across GUI applications ranging from web automation to mobile systems. However, MLAs introduce critical trustworthiness challenges that extend far beyond traditional language models' limitations, as they can directly modify digital states and trigger irreversible real-world consequences. Existing benchmarks inadequately tackle these unique challenges posed by MLAs' actionable outputs, long-horizon uncertainty and multimodal attack vectors. In this paper, we introduce MLA-Trust, the first comprehensive and unified framework that evaluates the MLA trustworthiness across four principled dimensions: truthfulness, controllability, safety and privacy. We utilize websites and mobile applications as realistic testbeds, designing 34 high-risk interactive tasks and curating rich evaluation datasets. Large-scale experiments involving 13 state-of-the-art agents reveal previously unexplored trustworthiness vulnerabilities unique to multimodal interactive scenarios. For instance, proprietary and open-source GUI-interacting MLAs pose more severe trustworthiness risks than static MLLMs, particularly in high-stakes domains; the transition from static MLLMs into interactive MLAs considerably compromises trustworthiness, enabling harmful content generation in multi-step interactions that standalone MLLMs would typically prevent; multi-step execution, while enhancing the adaptability of MLAs, involves latent nonlinear risk accumulation across successive interactions, circumventing existing safeguards and resulting in unpredictable derived risks. Moreover, we present an extensible toolbox to facilitate continuous evaluation of MLA trustworthiness across diverse interactive environments.

Large Language Models (LLMs) excel in zero-shot and few-shot tasks, but achieving similar performance with encoder-only models like BERT and RoBERTa has been challenging due to their architecture. However, encoders offer advantages such as lower computational and memory costs. Recent work adapts them for zero-shot generalization using Statement Tuning, which reformulates tasks into finite templates. We extend this approach to multilingual NLP, exploring whether encoders can achieve zero-shot cross-lingual generalization and serve as efficient alternatives to memory-intensive LLMs for low-resource languages. Our results show that state-of-the-art encoder models generalize well across languages, rivaling multilingual LLMs while being more efficient. We also analyze multilingual Statement Tuning dataset design, efficiency gains, and language-specific generalization, contributing to more inclusive and resource-efficient NLP models. We release our code and models.

--The rapid expansion of social media platforms has significantly increased the dissemination of forged content and misinformation, making the detection of fake news a critical area of research. Although fact-checking efforts predominantly focus on English-language news, there is a noticeable gap in resources and strategies to detect news in regional languages, such as Urdu. Advanced Fake News Detection (FND) techniques rely heavily on large, accurately labeled datasets. However, FND in under-resourced languages like Urdu faces substantial challenges due to the scarcity of extensive corpora and the lack of validated lexical resources. Current Urdu fake news datasets are often domain-specific and inaccessible to the public. They also lack human verification, relying mainly on unverified English-to-Urdu translations, which compromises their reliability in practical applications. This study highlights the necessity of developing reliable, expert-verified, and domain-independent Urdu-enhanced FND datasets to improve fake news detection in Urdu and other resource-constrained languages. This paper presents the first benchmark large FND dataset for Urdu news, which is publicly available for validation and deep analysis. We also evaluate this dataset using multiple state-of-the-art pre-trained large language models (LLMs), such as XLNet, mBERT, XLM-RoBERT a, RoBERT a, DistilBERT, and DeBERT a. Additionally, we propose a unified LLM model that outperforms the others with different embedding and feature extraction techniques. The performance of these models is compared based on accuracy, F1 score, precision, recall, and human judgment for vetting the sample results of news. The proposed model outperforms advanced machine learning and deep learning models previously used in the literature for fake news detection.

Forecasting future events has significant decision-relevance, as having a well-calibrated probabilistic estimation of the risk of a future pandemic, a conflict, or an emerging technology is crucial in making decisions under uncertainty. Current best practices for forecasting rely on aggregating the judgemental forecasts of experienced forecasters (Tetlock & Gardner 2016), a process that is both lengthy and expensive, though it promises to produce valuable input into decision-making processes (Mellers et al, 2019; Tetlock et al. 2014). Recent work has applied frontier large language models (LLM) to forecasting, testing a variety of research questions, such as whether LLMs are able to match human forecasting performance, what determines their prediction capabilities, and how these capabilities may be increased. For example, previous work looked at retrieval-augmented systems (Halawi et al. 2024), aggregation of multiple models (Schoenegger et al. 2024), ranking-based context retrieval systems (Yan et al. 2024), or applications of reinforcement learning (Turtel et al. 2025b). While many of these approaches have resulted in increased forecasting performance, the current performance of frontier models still trails experienced forecaster aggregates on ForecastBench (Karger et al. 2024). Many such approaches have focused on specific aspects in designing forecasting pipelines such as effective news aggregation (Wang et al. 2025) or fine-tuning on model self-play output (Turtel et al. 2025).

Cross-lingual vocabulary transfer plays a promising role in adapting pre-trained language models to new languages, including low-resource languages. Existing approaches that utilize monolingual or parallel corpora face challenges when applied to languages with limited resources. In this work, we propose a simple yet effective vocabulary transfer method that utilizes bilingual dictionaries, which are available for many languages, thanks to descriptive linguists. Our proposed method leverages a property of BPE tokenizers where removing a subword from the vocabulary causes a fallback to shorter subwords. The embeddings of target subwords are estimated iteratively by progressively removing them from the tokenizer. The experimental results show that our approach outperforms existing methods for low-resource languages, demonstrating the effectiveness of a dictionary-based approach for cross-lingual vocabulary transfer.

Online form filling is a common yet labor-intensive task involving extensive keyboard and mouse interactions. Despite the long-standing vision of automating this process with "one click", existing tools remain largely rule-based and lack generalizable, generative capabilities. Recent advances in Multimodal Large Language Models (MLLMs) have enabled promising agents for GUI-related tasks in general-purpose scenarios. However, they struggle with the unique challenges of form filling, such as flexible layouts and the difficulty of aligning textual instructions with on-screen fields. To bridge this gap, we formally define the form-filling task and propose FormFactory, an interactive benchmarking suite comprising a web-based interface, backend evaluation module, and carefully constructed dataset. Our benchmark covers diverse real-world scenarios, incorporates various field formats, and simulates high-fidelity form interactions. We conduct a comprehensive evaluation of state-of-the-art MLLMs and observe that no model surpasses 5% accuracy, underscoring the inherent difficulty of the task. These findings also reveal significant limitations in current models' visual layout reasoning and field-value alignment abilities. We hope our benchmark can serve as a stepping stone for further research into robust, practical form-filling agents.

Rational speakers are supposed to know what they know and what they do not know, and to generate expressions matching the strength of evidence. In contrast, it is still a challenge for current large language models to generate corresponding utterances based on the assessment of facts and confidence in an uncertain real-world environment. While it has recently become popular to estimate and calibrate confidence of LLMs with verbalized uncertainty, what is lacking is a careful examination of the linguistic knowledge of uncertainty encoded in the latent space of LLMs. In this paper, we draw on typological frameworks of epistemic expressions to evaluate LLMs' knowledge of epistemic modality, using controlled stories. Our experiments show that the performance of LLMs in generating epistemic expressions is limited and not robust, and hence the expressions of uncertainty generated by LLMs are not always reliable. To build uncertainty-aware LLMs, it is necessary to enrich semantic knowledge of epistemic modality in LLMs.

In this paper, we propose the first multilingual study on definition modeling. We use monolingual dictionary data for four new languages (Spanish, French, Portuguese, and German) and perform an in-depth empirical study to test the performance of pre-trained multilingual language models on definition modeling of monosemic words when finetuned on this data. Furthermore, we use a zero-shot approach to test the multilingual capabilities of two popular chat-based Large Language Models (LLMs) in the task. Results show that multilingual language models can perform on-pair with English but cannot leverage potential cross-lingual synergies, with LLMs generally offering better performance overall. A comprehensive human evaluation of the LLM-generated definition highlights the zero and few-shot capabilities of these models in this new task, also showing their shortcomings. Finally, we show that performance on our task via BERTScore strongly correlates to the performance on multilingual LLM benchmarks, suggesting that our task offers a viable compute-constrained, stable and natural alternative to these.

Large Language Model (LLM) agents have demonstrated impressive capabilities in handling complex interactive problems. Existing LLM agents mainly generate natural language plans to guide reasoning, which is verbose and inefficient. NL plans are also tailored to specific tasks and restrict agents' ability to generalize across similar tasks. To this end, we explore pseudocode-style plans (P-code Plan) to capture the structural logic of reasoning. We find that P-code Plan empowers LLM agents with stronger generalization ability and more efficiency. Inspired by this finding, we propose a pseudocode-style Planning Guided Preference Optimization method called PGPO for effective agent learning. With two planning-oriented rewards, PGPO further enhances LLM agents' ability to generate high-quality P-code Plans and subsequent reasoning. Experiments show that PGPO achieves superior performance on representative agent benchmarks and outperforms the current leading baselines. Analyses reveal the advantage of PGPO in reducing action errors and omissions during reasoning.

Computational models of pragmatic language use have traditionally relied on hand-specified sets of utterances and meanings, limiting their applicability to real-world language use. We propose a neuro-symbolic framework that enhances probabilistic cognitive models by integrating LLM-based modules to propose and evaluate key components in natural language, eliminating the need for manual specification. Through a classic case study of pragmatic question-answering, we systematically examine various approaches to incorporating neural modules into the cognitive model -- from evaluating utilities and literal semantics to generating alternative utterances and goals. We find that hybrid models can match or exceed the performance of traditional probabilistic models in predicting human answer patterns. However, the success of the neuro-symbolic model depends critically on how LLMs are integrated: while they are particularly effective for proposing alternatives and transforming abstract goals into utilities, they face challenges with truth-conditional semantic evaluation. This work charts a path toward more flexible and scalable models of pragmatic language use while illuminating crucial design considerations for balancing neural and symbolic components.