Large Language Models (LLMs) face significant challenges in edge deployment due to their massive parameter scale. Vector Quantization (VQ), a clustering-based quantization method, serves as a prevalent solution to this issue for its extremely low-bit (even at 2-bit) and considerable accuracy. Since a vector is a quantity in mathematics and physics that has both direction and magnitude, existing VQ works typically quantize them in a coupled manner. However, we find that direction exhibits significantly greater sensitivity to quantization compared to the magnitude. For instance, when separately clustering the directions and magnitudes of weight vectors in LLaMA-2-7B, the accuracy drop of zero-shot tasks are 46.5\% and 2.3\%, respectively. This gap even increases with the reduction of clustering centers. Further, Euclidean distance, a common metric to access vector similarities in current VQ works, places greater emphasis on reducing the magnitude error. This property is contrary to the above finding, unavoidably leading to larger quantization errors. To these ends, this paper proposes Polar Coordinate Decoupled Vector Quantization (PCDVQ), an effective and efficient VQ framework consisting of two key modules: 1) Polar Coordinate Decoupling (PCD), which transforms vectors into their polar coordinate representations and perform independent quantization of the direction and magnitude parameters.2) Distribution Aligned Codebook Construction (DACC), which optimizes the direction and magnitude codebooks in accordance with the source distribution. Experimental results show that PCDVQ outperforms baseline methods at 2-bit level by at least 1.5\% zero-shot accuracy, establishing a novel paradigm for accurate and highly compressed LLMs.

Long context large language models (LLMs) are deployed in many real-world applications such as RAG, agent, and broad LLM-integrated applications. Given an instruction and a long context (e.g., documents, PDF files, webpages), a long context LLM can generate an output grounded in the provided context, aiming to provide more accurate, up-to-date, and verifiable outputs while reducing hallucinations and unsupported claims. This raises a research question: how to pinpoint the texts (e.g., sentences, passages, or paragraphs) in the context that contribute most to or are responsible for the generated output by an LLM? This process, which we call context traceback, has various real-world applications, such as 1) debugging LLM-based systems, 2) conducting post-attack forensic analysis for attacks (e.g., prompt injection attack, knowledge corruption attacks) to an LLM, and 3) highlighting knowledge sources to enhance the trust of users towards outputs generated by LLMs. When applied to context traceback for long context LLMs, existing feature attribution methods such as Shapley have sub-optimal performance and/or incur a large computational cost. In this work, we develop TracLLM, the first generic context traceback framework tailored to long context LLMs. Our framework can improve the effectiveness and efficiency of existing feature attribution methods. To improve the efficiency, we develop an informed search based algorithm in TracLLM. We also develop contribution score ensemble/denoising techniques to improve the accuracy of TracLLM. Our evaluation results show TracLLM can effectively identify texts in a long context that lead to the output of an LLM. Our code and data are at: https://github.com/Wang-Yanting/TracLLM.

The rapid progress of Large Language Models (LLMs) has transformed the field of Natural Language Processing (NLP). However, these advancements have primarily concentrated on high-resource languages, leaving many low-resource languages, particularly African languages, largely overlooked. Africa has over 2,000 languages [Ethnologue, 2025], the majority of which face significant challenges such as a lack of data, limited computational resources, insufficient NLP tools, and the absence of standardized benchmarks. This study presents a three-stage review to evaluate LLMs' current status, challenges, and prospects for African languages. The first stage investigates both commercial and open-source LLMs models with more than 7 billion parameters regarding their support for African languages [Wang et al., 2024]. The second stage examines foundational multilingual models that have significantly influenced NLP research and development.

Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference. However, applying elaborate reasoning for all queries often results in substantial computational inefficiencies, particularly when many problems admit straightforward solutions. This motivates an open question: Can LLMs learn when to think? To answer this, we propose Thinkless, a learnable framework that empowers an LLM to adaptively select between short-form and long-form reasoning, based on both task complexity and the model's ability. Thinkless is trained under a reinforcement learning paradigm and employs two control tokens, for concise responses and for detailed reasoning. At the core of our method is a Decoupled Group Relative Policy Optimization (DeGRPO) algorithm, which decomposes the learning objective of hybrid reasoning into two components: (1) a control token loss that governs the selection of the reasoning mode, and (2) a response loss that improves the accuracy of the generated answers. This decoupled formulation enables fine-grained control over the contributions of each objective, stabilizing training and effectively preventing collapse observed in vanilla GRPO. Empirically, on several benchmarks such as Minerva Algebra, MATH-500, and GSM8K, Thinkless is able to reduce the usage of long-chain thinking by 50% - 90%, significantly improving the efficiency of Reasoning Language Models. The code is available at https://github.com/VainF/Thinkless

Sign up for the Slatest to get the most insightful analysis, criticism, and advice out there, delivered to your inbox daily. This spring's hot topic of conversation for my colleagues in higher ed was that "Everyone Is Cheating Their Way Through College" article in New York magazine. Most of the fellow professors I spoke with about this were horrified by how often students now can and do let A.I. write their papers. Others are joining their students in asking, Why not? A surprising coalition--William Shakespeare and 17th-century scribes, as well as 21st-century elementary school teachers, anti-fascist scholars, and epidemiologists--would tell you why not. A key principle for 17th-century scholars transcribing or translating classical or biblical texts was lectio difficilior potior: The reading that is stranger is stronger.

Large Language Models (LLMs) ) have demonstrated promise in boosting productivity across AI-powered tools, yet existing benchmarks like Massive Multitask Language Understanding (MMLU) inadequately assess enterprise-specific task complexities. We propose a 14-task framework grounded in Bloom's Taxonomy to holistically evaluate LLM capabilities in enterprise contexts. To address challenges of noisy data and costly annotation, we develop a scalable pipeline combining LLM-as-a-Labeler, LLM-as-a-Judge, and corrective retrieval-augmented generation (CRAG), curating a robust 9,700-sample benchmark. Evaluation of six leading models shows open-source contenders like DeepSeek R1 rival proprietary models in reasoning tasks but lag in judgment-based scenarios, likely due to overthinking. Our benchmark reveals critical enterprise performance gaps and offers actionable insights for model optimization. This work provides enterprises a blueprint for tailored evaluations and advances practical LLM deployment.

As the demand for on-device Large Language Model (LLM) inference grows, energy efficiency has become a major concern, especially for battery-limited mobile devices. Our analysis shows that the memory-bound LLM decode phase dominates energy use, and yet most existing works focus on accelerating the prefill phase, neglecting energy concerns. We introduce Adaptive Energy-Centric Core Selection (AECS) and integrate it into MNN to create the energy-efficient version, MNN-AECS, the first engine-level system solution without requiring root access or OS modifications for energy-efficient LLM decoding. MNN-AECS is designed to reduce LLM decoding energy while keeping decode speed within an acceptable slowdown threshold by dynamically selecting low-power CPU cores. MNN-AECS is evaluated across 5 Android and 2 iOS devices on 5 popular LLMs of various sizes. Compared to original MNN, MNN-AECS cuts down energy use by 23% without slowdown averaged over all 7 devices and 4 datasets. Against other engines, including llama.cpp, executorch, mllm, and MediaPipe, MNN-AECS delivers 39% to 78% energy saving and 12% to 363% speedup on average.

A growing fraction of all code is sampled from Large Language Models (LLMs). We investigate the problem of attributing code generated by language models using hypothesis testing to leverage established techniques and guarantees. Given a set of samples $S$ and a suspect model $\mathcal{L}^*$, our goal is to assess the likelihood of $S$ originating from $\mathcal{L}^*$. Due to the curse of dimensionality, this is intractable when only samples from the LLM are given: to circumvent this, we use both samples and density estimates from the LLM, a form of access commonly available. We introduce $\mathsf{Anubis}$, a zero-shot attribution tool that frames attribution as a distribution testing problem. Our experiments on a benchmark of code samples show that $\mathsf{Anubis}$ achieves high AUROC scores ( $\ge0.9$) when distinguishing between LLMs like DeepSeek-Coder, CodeGemma, and Stable-Code using only $\approx 2000$ samples.

Background The increasing adoption of Artificial Intelligence (AI) in healthcare has sparked growing concerns about its environmental and ethical implications. Commercial Large Language Models (LLMs), such as ChatGPT and DeepSeek, require substantial resources, while the utilization of these systems for medical purposes raises critical issues regarding patient privacy and safety. Methods We developed a customizable Retrieval-Augmented Generation (RAG) framework for medical tasks, which monitors its energy usage and CO2 emissions. This system was then used to create RAGs based on various open-source LLMs. The tested models included both general purpose models like llama3.1:8b and medgemma-4b-it, which is medical-domain specific. The best RAGs performance and energy consumption was compared to DeepSeekV3-R1 and OpenAIs o4-mini model. A dataset of medical questions was used for the evaluation. Results Custom RAG models outperformed commercial models in accuracy and energy consumption. The RAG model built on llama3.1:8B achieved the highest accuracy (58.5%) and was significantly better than other models, including o4-mini and DeepSeekV3-R1. The llama3.1-RAG also exhibited the lowest energy consumption and CO2 footprint among all models, with a Performance per kWh of 0.52 and a total CO2 emission of 473g. Compared to o4-mini, the llama3.1-RAG achieved 2.7x times more accuracy points per kWh and 172% less electricity usage while maintaining higher accuracy. Conclusion Our study demonstrates that local LLMs can be leveraged to develop RAGs that outperform commercial, online LLMs in medical tasks, while having a smaller environmental impact. Our modular framework promotes sustainable AI development, reducing electricity usage and aligning with the UNs Sustainable Development Goals.

Retrieval-Augmented Generation (RAG) systems and large language model (LLM)-powered chatbots have significantly advanced conversational AI by combining generative capabilities with external knowledge retrieval. Despite their success, enterprise-scale deployments face critical challenges, including diverse user queries, high latency, hallucinations, and difficulty integrating frequently updated domain-specific knowledge. This paper introduces a novel hybrid framework that integrates RAG with intent-based canned responses, leveraging predefined high-confidence responses for efficiency while dynamically routing complex or ambiguous queries to the RAG pipeline. Our framework employs a dialogue context manager to ensure coherence in multi-turn interactions and incorporates a feedback loop to refine intents, dynamically adjust confidence thresholds, and expand response coverage over time. Experimental results demonstrate that the proposed framework achieves a balance of high accuracy (95\%) and low latency (180ms), outperforming RAG and intent-based systems across diverse query types, positioning it as a scalable and adaptive solution for enterprise conversational AI applications.