Code Generation

Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo et al.

We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to span a wide range of p…

Ziyin Zhang, Zihan Liao, Hang Yu et al.

We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available h…

Zhuolin Yang, Zihan Liu, Yang Chen et al.

We introduce Nemotron-Cascade 2, an open 30B MoE model with 3B activated parameters that delivers best-in-class reasoning and strong agentic capabilities. Despite its compact size, its mathematical an…

Qiawen Ella Liu, Marina Dubova, Henry Conklin et al.

Are large language models (LLMs) creative in the same way humans are, and can the same interventions increase creativity in both? We evaluate a promising but largely untested intervention for creativi…

Maksym Del, Markus Kängsepp, Marharyta Domnich et al.

Uncertainty estimation is critical for deploying reasoning language models, yet remains poorly understood under extended chain-of-thought reasoning. We study parallel sampling as a fully black-box app…

Swagat Padhan, Lakshya Jain, Bhavya Minesh Shah et al.

Robots collaborating with humans must convert natural language goals into actionable, physically grounded decisions. For example, executing a command such as "go two meters to the right of the fridge"…

Carlos Hinojosa, Clemens Grange, Bernard Ghanem

Vision-language models (VLMs) are increasingly deployed in real-world and embodied settings where safety decisions depend on visual context. However, it remains unclear which visual evidence drives th…

Yilin Wang, Yuchun Fan, Jiaoyang Li et al.

Retrieval-augmented generation (RAG) systems have made significant progress in solving complex multi-hop question answering (QA) tasks in the English scenario. However, RAG systems inevitably face the…

Yogesh Agrawal, Aniruddha Dutta, Md Mahadi Hasan et al.

Real-world financial decision-making is a challenging problem that requires reasoning over heterogeneous signals, including company fundamentals derived from regulatory filings and trading signals com…

Qiawen Ella Liu, Raja Marjieh, Jian-Qiao Zhu et al.

Four-term word analogies (A:B::C:D) are classically modeled geometrically as ''parallelograms,'' yet recent work suggests this model poorly captures how humans produce analogies, with simple local-sim…

Jonathan Lys, Vincent Gripon, Bastien Pasdeloup et al.

Discrete diffusion models are promising alternatives to autoregressive approaches for text generation, yet their decoding methods remain under-studied. Standard decoding methods for autoregressive mod…

Zou Qiang

Large language models (LLMs) demonstrate strong generative capabilities but remain vulnerable to hallucination and unreliable reasoning under adversarial prompting. Existing safety approaches -- such …

Chonghan Liu, Yimin Du, Qi An et al.

Large language models frequently exhibit suboptimal performance on low resource languages, primarily due to inefficient subword segmentation and systemic training data imbalances. In this paper, we pr…

Madeline Bittner, Dina Demner-Fushman, Yasmeen Shabazz et al.

Health literacy is a critical determinant of patient outcomes, yet current screening tools are not always feasible and differ considerably in the number of items, question format, and dimensions of he…

Hangeol Chang, Changsun Lee, Seungjoon Rho et al.

Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by grounding generation in external, non-parametric knowledge. However, when a task requires choosing among competing options…

Zikang Ding, Junchi Yao, Junhao Li et al.

Large language models (LLMs) exhibit pronounced social biases. Output-level or data-optimization--based debiasing methods cannot fully resolve these biases, and many prior works have shown that biases…

Qiang Li, XiangRui Zhang, Haining Wang

Binary vulnerability analysis is increasingly performed by LLM-based agents in an iterative, multi-pass manner, with the model as the core decision-maker. However, how such systems organize exploratio…

Gagan Bhatia, Ahmad Muhammad Isa, Maxime Peyrard et al.

We present MultiTempBench, a multilingual temporal reasoning benchmark spanning three tasks, date arithmetic, time zone conversion, and temporal relation extraction across five languages (English, Ger…

Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang et al.

Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-training and how thi…

Xiao Feng, Bo Han, Zhanke Zhou et al.

Reinforcement learning (RL) holds significant promise for enhancing the agentic reasoning capabilities of large language models (LLMs) with external environments. However, the inherent sparsity of ter…

Gabriele Carrino, Andrea Sassella, Nicolo Brunello et al.

Recent advances in large language models (LLMs) highlight the importance of post training techniques for improving reasoning and mathematical ability. Group Relative Policy Optimization (GRPO) has sho…

Yana Veitsman, Yihong Liu, Hinrich Schütze

Better cross-lingual alignment is often assumed to yield better cross-lingual transfer. However, explicit alignment techniques -- despite increasing embedding similarity -- frequently fail to improve …

Rudra Jadhav, Janhavi Danve, Sonalika Shaw

As large language models (LLMs) are increasingly deployed as automated graders in educational settings, concerns about fairness and bias in their evaluations have become critical. This study investiga…

Vedant Pandya

Knowledge-grounded dialogue systems aim to generate informative, contextually relevant responses by conditioning on external knowledge sources. However, most existing approaches focus exclusively on E…

Mingyang Liu, Yongshan Chen, Zhiyuan Fan et al.

Online learning in arbitrary, and possibly adversarial, environments has been extensively studied in sequential decision-making, and it is closely connected to equilibrium computation in game theory. …

Carlos Rafael Catalan, Patricia Nicole Monderin, Lheane Marie Dizon et al.

Popular language learning applications such as Duolingo use large language models (LLMs) to generate lessons for its users. Most lessons focus on general real-world scenarios such as greetings, orderi…

Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim et al.

The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must culminate in formally s…

Skyler Seto, Pierre Ablin, Anastasiia Filippova et al.

Language models achieve impressive performance on a variety of knowledge, language, and reasoning tasks due to the scale and diversity of pretraining data available. The standard training recipe is a …

Dimitrios Georgousis, Maria Lymperaiou, Angeliki Dimitriou et al.

We evaluate Large Language Models (LLMs) in repeated game-theoretic settings to assess whether strategic performance reflects genuine reasoning or reliance on memorized patterns. We consider two canon…

Chenyang Gu, Jiahao Cheng, Meicong Zhang et al.

Scientific ideation aims to propose novel solutions within a given scientific context. Existing LLM-based agentic approaches emulate human research workflows, yet inadequately model scientific reasoni…