We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing strategy to strengthen the base model's reasoning potential. MiMo-7B-Base is pre-trained on 25 trillion tokens, with additional Multi-Token Prediction objective for enhanced performance and accelerated inference speed. During post-training, we curate a dataset of 130K verifiable mathematics and programming problems for reinforcement learning, integrating a test-difficulty-driven code-reward scheme to alleviate sparse-reward issues and employing strategic data resampling to stabilize training. Extensive evaluations show that MiMo-7B-Base possesses exceptional reasoning potential, outperforming even much larger 32B models. The final RL-tuned model, MiMo-7B-RL, achieves superior performance on mathematics, code and general reasoning tasks, surpassing the performance of OpenAI o1-mini. The model checkpoints are available at https://github.com/xiaomimimo/MiMo.

In this technical report, we empirically investigate the relationship between linguistic fluency and domain knowledge in the context of continual learning with large language models (LLMs). Specifically, we enhance the linguistic fluency of the Gemma2 LLM for the Lithuanian language by autoregressively pretraining its full parameter set on the first 10\% of the Lithuanian language component of the CulturaX dataset. To prevent catastrophic forgetting of the model's existing domain knowledge, we apply Elastic Weight Consolidation (EWC), leveraging Fisher information estimated using data from the Massive Multitask Language Understanding (MMLU) benchmark. In the post-training evaluations, we assess linguistic fluency through perplexity and evaluate domain knowledge using accuracy on a suite of language understanding benchmarks, including ARC-Easy, Belebele, GSM8K, HellaSwag, MMLU, TruthfulQA, and Winogrande, in both English and Lithuanian. The empirical results demonstrate that EWC not only mitigates catastrophic forgetting by preserving the model's performance in terms of both linguistic fluency and domain knowledge but also improves or maintains these capabilities for the newly added Lithuanian language. These findings highlight the potential for more efficient adaptation of general-purpose LLMs to under-represented languages without requiring access to the original training data. The accompanying codebase is openly accessible at https://github.com/Neurotechnology/LLM_EWC.

Regulatory efforts to govern large language model (LLM) development have predominantly focused on restricting access to high-performance computational resources. This study evaluates the efficacy of such measures by examining whether LLM capabilities can advance through algorithmic innovation in compute-constrained environments. We propose a novel framework distinguishing compute-dependent innovations--which yield disproportionate benefits at high compute--from compute-independent innovations, which improve efficiency across compute scales. The impact is quantified using Compute-Equivalent Gain (CEG). Experimental validation with nanoGPT models confirms that compute-independent advancements yield significant performance gains (e.g., with combined CEG up to $3.5\times$) across the tested scales. In contrast, compute-dependent advancements were detrimental to performance at smaller experimental scales, but showed improved CEG (on par with the baseline) as model size increased, a trend consistent with their definition of yielding primary benefits at higher compute. Crucially, these findings indicate that restrictions on computational hardware, while potentially slowing LLM progress, are insufficient to prevent all capability gains driven by algorithmic advancements. We argue that effective AI oversight must therefore incorporate mechanisms for understanding, anticipating, and potentially guiding algorithmic research, moving beyond a singular focus on hardware. The proposed framework also serves as an analytical tool for forecasting AI progress.

Large language models (LLMs) achieve remarkable performance across numerous tasks by using a diverse array of adaptation strategies. However, optimally selecting a model and adaptation strategy under resource constraints is challenging and often requires extensive experimentation. We investigate whether it is possible to accurately predict both performance and cost without expensive trials. We formalize the strategy selection problem for LLMs and introduce COSMOS, a unified prediction framework that efficiently estimates adaptation outcomes at minimal cost. We instantiate and study the capability of our framework via a pair of powerful predictors: embedding-augmented lightweight proxy models to predict fine-tuning performance, and low-sample scaling laws to forecast retrieval-augmented in-context learning. Extensive evaluation across eight representative benchmarks demonstrates that COSMOS achieves high prediction accuracy while reducing computational costs by 92.72% on average, and up to 98.71% in resource-intensive scenarios. Our results show that efficient prediction of adaptation outcomes is not only feasible but can substantially reduce the computational overhead of LLM deployment while maintaining performance standards.

Neural machine translation (NMT) systems typically employ maximum a posteriori (MAP) decoding to select the highest-scoring translation from the distribution mass. However, recent evidence highlights the inadequacy of MAP decoding, often resulting in low-quality or even pathological hypotheses -- the decoding objective is not aligned with real-world translation quality. This paper proposes calibrating hypothesis likelihoods with translation quality from a distribution view by directly optimizing their Pearson correlation -- thereby enhancing the effectiveness of translation decoding. With our method, translation on large language models (LLMs) improves substantially after limited training (2K instances per direction). This improvement is orthogonal to those achieved through supervised fine-tuning, leading to substantial gains across a broad range of metrics and human evaluations -- even when applied to top-performing translation-specialized LLMs fine-tuned on high-quality translation data, such as Tower, or when compared to recent preference optimization methods, like CPO. Moreover, the calibrated translation likelihood can directly serve as a strong proxy for translation quality, closely approximating or even surpassing some state-of-the-art translation quality estimation models, like CometKiwi. Lastly, our in-depth analysis demonstrates that calibration enhances the effectiveness of MAP decoding, thereby enabling greater efficiency in real-world deployment. The resulting state-of-the-art translation model, which covers 10 languages, along with the accompanying code and human evaluation data, has been released to the community: https://github.com/moore3930/calibrating-llm-mt.

Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data, thereby introducing new dimensions of potential attacks and complex risk combinations. In this paper, we begin with a detailed analysis aimed at disentangling risks through step-by-step reasoning within multimodal inputs. We find that systematic multimodal risk disentanglement substantially enhances the risk awareness of MLLMs. Via leveraging the strong discriminative abilities of multimodal risk disentanglement, we further introduce \textbf{DREAM} (\textit{\textbf{D}isentangling \textbf{R}isks to \textbf{E}nhance Safety \textbf{A}lignment in \textbf{M}LLMs}), a novel approach that enhances safety alignment in MLLMs through supervised fine-tuning and iterative Reinforcement Learning from AI Feedback (RLAIF). Experimental results show that DREAM significantly boosts safety during both inference and training phases without compromising performance on normal tasks (namely oversafety), achieving a 16.17\% improvement in the SIUO safe\&effective score compared to GPT-4V. The data and code are available at https://github.com/Kizna1ver/DREAM.

The rise of Large Language Models (LLMs) has revolutionized Graphical User Interface (GUI) automation through LLM-powered GUI agents, yet their ability to process sensitive data with limited human oversight raises significant privacy and security risks. This position paper identifies three key risks of GUI agents and examines how they differ from traditional GUI automation and general autonomous agents. Despite these risks, existing evaluations focus primarily on performance, leaving privacy and security assessments largely unexplored. We review current evaluation metrics for both GUI and general LLM agents and outline five key challenges in integrating human evaluators for GUI agent assessments. To address these gaps, we advocate for a human-centered evaluation framework that incorporates risk assessments, enhances user awareness through in-context consent, and embeds privacy and security considerations into GUI agent design and evaluation.

--In recent years, Unsupervised Domain Adaptation (UDA) has gained significant attention in the field of Natural Language Processing (NLP) owing to its ability to enhance model generalization across diverse domains. However, its application for knowledge transfer between distinct legal domains remains largely unexplored. T o address the challenges posed by lengthy and complex legal texts and the limited availability of large-scale annotated datasets, we propose JurisCTC, a novel model designed to improve the accuracy of Legal Judgment Prediction (LJP) tasks. Unlike existing approaches, JurisCTC facilitates effective knowledge transfer across various legal domains and employs contrastive learning to distinguish samples from different domains. Specifically, for the LJP task, we enable knowledge transfer between civil and criminal law domains. Compared to other models and specific large language models (LLMs), JurisCTC demonstrates notable advancements, achieving peak accuracies of 76.59% and 78.83%, respectively. Legal Judgment Prediction (LJP) refers to the task of forecasting court outcomes based on the facts of a legal case, as well as other relevant information such as arguments and claims presented in the case description. This field aims to leverage computational techniques to predict judicial decisions, offering significant benefits across various legal contexts. Automated LJP systems have considerable practical value: they can assist legal professionals in analyzing cases and providing consultation services to the public, thereby reducing legal costs and improving access to justice.

This paper introduces NorEval, a new and comprehensive evaluation suite for large-scale standardized benchmarking of Norwegian generative language models (LMs). NorEval consists of 24 high-quality human-created datasets -- of which five are created from scratch. In contrast to existing benchmarks for Norwegian, NorEval covers a broad spectrum of task categories targeting Norwegian language understanding and generation, establishes human baselines, and focuses on both of the official written standards of the Norwegian language: Bokmål and Nynorsk. All our datasets and a collection of over 100 human-written prompts are integrated into LM Evaluation Harness, ensuring flexible and reproducible evaluation. We describe the NorEval design and present the results of benchmarking 19 open-source pre-trained and instruction-tuned LMs for Norwegian in various scenarios. Our benchmark, evaluation framework, and annotation materials are publicly available.

Accurate and verifiable large language model (LLM) simulations of human research subjects promise an accessible data source for understanding human behavior and training new AI systems. However, results to date have been limited, and few social scientists have adopted this method. In this position paper, we argue that the promise of LLM social simulations can be achieved by addressing five tractable challenges. We ground our argument in a review of empirical comparisons between LLMs and human research subjects, commentaries on the topic, and related work. We identify promising directions, including context-rich prompting and fine-tuning with social science datasets. We believe that LLM social simulations can already be used for pilot and exploratory studies, and more widespread use may soon be possible with rapidly advancing LLM capabilities. Researchers should prioritize developing conceptual models and iterative evaluations to make the best use of new AI systems.