Decoding strategies significantly influence the quality and diversity of the generated texts in large language models (LLMs), yet their impact on computational resource consumption, particularly GPU energy usage, is insufficiently studied. This paper investigates the relationship between text generation decoding methods and energy efficiency, focusing on the trade-off between generation quality and GPU energy consumption across diverse tasks and decoding configurations. By benchmarking multiple strategies across different text generation tasks, such as Translation, Code Summarization, and Math Problem Solving, we reveal how selecting appropriate decoding techniques with their tuned hyperparameters affects text quality and has measurable implications for resource utilization, emphasizing the need for balanced optimization. To the best of our knowledge, this study is among the first to explore decoding strategies in LLMs through the lens of energy consumption, offering actionable insights for designing resource-aware applications that maintain high-quality text generation.
DeepSeek-R1, known for its low training cost and exceptional reasoning capabilities, has achieved state-of-the-art performance on various benchmarks. However, detailed evaluations for DeepSeek Series models from the perspective of real-world applications are lacking, making it challenging for users to select the most suitable DeepSeek models for their specific needs. To address this gap, we presents the first comprehensive evaluation of the DeepSeek and its related models (including DeepSeek-V3, DeepSeek-R1, DeepSeek-R1-Distill-Qwen series, DeepSeek-R1-Distill-Llama series, their corresponding 4-bit quantized models, and the reasoning model QwQ-32B) using our enhanced A-Eval benchmark, A-Eval-2.0. Our systematic analysis reveals several key insights: (1) Given identical model architectures and training data, larger parameter models demonstrate superior performance, aligning with the scaling law. However, smaller models may achieve enhanced capabilities when employing optimized training strategies and higher-quality data; (2) Reasoning-enhanced model show significant performance gains in logical reasoning tasks but may underperform in text understanding and generation tasks; (3) As the data difficulty increases, distillation or reasoning enhancements yield higher performance gains for the models. Interestingly, reasoning enhancements can even have a negative impact on simpler problems; (4) Quantization impacts different capabilities unevenly, with significant drop on logical reasoning and minimal impact on text generation. Based on these results and findings, we design an model selection handbook enabling users to select the most cost-effective models without efforts.
Recently, a plethora of works have proposed inference-time algorithms (e.g. best-of-n), which incorporate verifiers to assist the generation process. Their quality-efficiency trade-offs have been empirically benchmarked on a variety of constrained generation tasks, but the algorithmic design landscape is still largely poorly understood. In this paper, we develop a mathematical framework for reasoning about constrained generation using a pre-trained language model generator oracle and a process verifier--which can decide whether a prefix can be extended to a string which satisfies the constraints of choice. We show that even in very simple settings, access to a verifier can render an intractable problem (information-theoretically or computationally) to a tractable one. In fact, we show even simple algorithms, like tokenwise rejection sampling, can enjoy significant benefits from access to a verifier. Empirically, we show that a natural modification of tokenwise rejection sampling, in which the sampler is allowed to "backtrack" (i.e., erase the final few generated tokens) has robust and substantive benefits over natural baselines (e.g. (blockwise) rejection sampling, nucleus sampling)--both in terms of computational efficiency, accuracy and diversity.
Uniform Meaning Representation (UMR) is a recently developed graph-based semantic representation, which expands on Abstract Meaning Representation (AMR) in a number of ways, in particular through the inclusion of document-level information and multilingual flexibility. In order to effectively adopt and leverage UMR for downstream tasks, efforts must be placed toward developing a UMR technological ecosystem. Though still limited amounts of UMR annotations have been produced to date, in this work, we investigate the first approaches to producing text from multilingual UMR graphs: (1) a pipeline conversion of UMR to AMR, then using AMR-to-text generation models, (2) fine-tuning large language models with UMR data, and (3) fine-tuning existing AMR-to-text generation models with UMR data. Our best performing model achieves a multilingual BERTscore of 0.825 for English and 0.882 for Chinese when compared to the reference, which is a promising indication of the effectiveness of fine-tuning approaches for UMR-to-text generation with even limited amounts of UMR data.
Large Language Models (LLMs) have made significant strides in natural language generation but often face challenges in tasks requiring precise calculations and structural analysis. This paper investigates the performance of state-of-the-art LLMs on language complexity measurement tasks, through the computation of the LIX readability metric and Average Dependency Distance (ADD). Using Swedish high school and university-level essays, we evaluate the models' abilities to compute LIX scores and perform dependency parsing, comparing their results to established ground truths. Our findings reveal that while all models demonstrate some capacity for these tasks, ChatGPT-o1-mini performs most consistently, achieving the highest accuracy in both LIX computation and dependency parsing. Additionally, we observe a strong significant correlation -0.875 p 0.026 (N=6) between the models' accuracy in computing LIX and their overall performance on the Massive Multitask Language Understanding (MMLU) benchmark. These results suggest that language complexity measurement abilities can serve as a noisy zero-shot proxies for assessing the general capabilities of LLMs, providing a practical method for model evaluation without the need for extensive benchmarking datasets.
As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical signals into language model-generated text without distorting the quality. In this paper, we introduce MCmark, a family of unbiased, Multi-Channel-based watermarks. MCmark works by partitioning the model's vocabulary into segments and promoting token probabilities within a selected segment based on a watermark key. We demonstrate that MCmark not only preserves the original distribution of the language model but also offers significant improvements in detectability and robustness over existing unbiased watermarks. Our experiments with widely-used language models demonstrate an improvement in detectability of over 10% using MCmark, compared to existing state-of-the-art unbiased watermarks. This advancement underscores MCmark's potential in enhancing the practical application of watermarking in AI-generated texts.
Modern large language models (LLMs) employ various forms of logical inference, both implicitly and explicitly, when addressing reasoning tasks. Understanding how to optimally leverage these inference paradigms is critical for advancing LLMs' reasoning capabilities. This paper adopts an exploratory approach by introducing a controlled evaluation environment for analogical reasoning -- a fundamental cognitive task -- that is systematically parameterized across three dimensions: modality (textual, visual, symbolic), difficulty (easy, medium, hard), and task format (multiple-choice or free-text generation). We analyze the comparative dynamics of inductive, abductive, and deductive inference pipelines across these dimensions, and demonstrate that our findings generalize to broader in-context learning tasks. Additionally, we investigate advanced paradigms such as hypothesis selection, verification, and refinement, revealing their potential to scale up logical inference in LLM reasoning. This exploratory study provides a foundation for future research in enhancing LLM reasoning through systematic logical inference strategies.
Large language models (LLMs) have significantly advanced the field of natural language generation. However, they frequently generate unverified outputs, which compromises their reliability in critical applications. In this study, we propose an innovative framework that combines structured biomedical knowledge with LLMs through a retrieval-augmented generation technique. Our system develops a thorough knowledge graph by identifying and refining causal relationships and named entities from medical abstracts related to age-related macular degeneration (AMD). Using a vector-based retrieval process and a locally deployed language model, our framework produces responses that are both contextually relevant and verifiable, with direct references to clinical evidence. Experimental results show that this method notably decreases hallucinations, enhances factual precision, and improves the clarity of generated responses, providing a robust solution for advanced biomedical chatbot applications.
Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and sliding window mechanisms\textemdash partially alleviate these issues but often require additional training or suffer from performance degradation with longer inputs. In this paper, we introduce \textbf{\textit{CacheFocus}}, a method that enhances length normalization and reduces inference latency without any further training. Our approach leverages query-independent, offline caching to efficiently reuse a Context KV Cache Store. We address the amplification of abnormal token distributions problem by re-positioning cached keys and introducing Layer-Adaptive Cache Pruning to discard low-relevance caches during pre-filling. Additionally, our Adaptive Positional Allocation Strategy dynamically reassigns cache positions to maximize the use of the available positional encoding range. Experiments on the Natural Questions and TriviaQA datasets demonstrate that CacheFocus outperforms alternative methods even when inputs exceed the $4$K limit of the \texttt{LLaMA-2} model, emphasizing its practical effectiveness for long-context LLMs. Moreover, even with large maximum input length of \texttt{Qwen2}, the performance of CacheFocus shows that it maintains consistent performance even as the number of documents increases, effectively managing long-text generation without degradation.
Large Language Models (LLMs) have demonstrated impressive capabilities in natural language processing tasks, such as text generation and semantic understanding. However, their performance on numerical reasoning tasks, such as basic arithmetic, numerical retrieval, and magnitude comparison, remains surprisingly poor. This gap arises from their reliance on surface-level statistical patterns rather than understanding numbers as continuous magnitudes. Existing benchmarks primarily focus on either linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical reasoning required in real-world scenarios. To bridge this gap, we propose NumericBench, a comprehensive benchmark to evaluate six fundamental numerical capabilities: number recognition, arithmetic operations, contextual retrieval, comparison, summary, and logical reasoning. NumericBench includes datasets ranging from synthetic number lists to the crawled real-world data, addressing challenges like long contexts, noise, and multi-step reasoning. Extensive experiments on state-of-the-art LLMs, including GPT-4 and DeepSeek, reveal persistent weaknesses in numerical reasoning, highlighting the urgent need to improve numerically-aware language modeling. The benchmark is released in: https://github.com/TreeAI-Lab/NumericBench.
Self-modulating mechanisms introduce dynamic adaptation capabilities within language models through contextual realignment strategies that influence token embedding trajectories across extended sequences. Contextual Flux is explored as an approach to embedding modulation, integrating an auxiliary gating mechanism within the self-attention framework to dynamically adjust token representations based on evolving contextual dependencies. The empirical analysis evaluates entropy variations, latent space realignments, and coherence stability to assess the extent to which self-regulation enhances text generation consistency while preserving generative flexibility. Quantitative assessments suggest that embedding shifts contribute to more structured adaptation in long-form sequences, with measured reductions in redundant phrase repetitions and improvements in thematic retention. Variability in contextual weight computation affects modulation stability, leading to differing levels of adaptation across diverse linguistic structures. The computational demands introduced through real-time embedding reconfiguration are examined in relation to model scalability, emphasizing the need for optimization strategies in high-volume generative applications. The findings suggest that while adaptive embedding updates improve certain aspects of coherence, their impact remains contingent on model capacity and input complexity.
While multilingual language models like XLM-R have advanced multilingualism in NLP, they still perform poorly in extremely low-resource languages. This situation is exacerbated by the fact that modern LLMs such as LLaMA and Qwen support far fewer languages than XLM-R, making text generation models non-existent for many languages in the world. To tackle this challenge, we propose a novel framework for adapting multilingual encoders to text generation in extremely low-resource languages. By reusing the weights between the encoder and the decoder, our framework allows the model to leverage the learned semantic space of the encoder, enabling efficient learning and effective generalization in low-resource languages. Applying this framework to four Chinese minority languages, we present XLM-SWCM, and demonstrate its superior performance on various downstream tasks even when compared with much larger models.
Integration of Brain-Computer Interfaces (BCIs) and Generative Artificial Intelligence (GenAI) has opened new frontiers in brain signal decoding, enabling assistive communication, neural representation learning, and multimodal integration. BCIs, particularly those leveraging Electroencephalography (EEG), provide a non-invasive means of translating neural activity into meaningful outputs. Recent advances in deep learning, including Generative Adversarial Networks (GANs) and Transformer-based Large Language Models (LLMs), have significantly improved EEG-based generation of images, text, and speech. This paper provides a literature review of the state-of-the-art in EEG-based multimodal generation, focusing on (i) EEG-to-image generation through GANs, Variational Autoencoders (VAEs), and Diffusion Models, and (ii) EEG-to-text generation leveraging Transformer based language models and contrastive learning methods. Additionally, we discuss the emerging domain of EEG-to-speech synthesis, an evolving multimodal frontier. We highlight key datasets, use cases, challenges, and EEG feature encoding methods that underpin generative approaches. By providing a structured overview of EEG-based generative AI, this survey aims to equip researchers and practitioners with insights to advance neural decoding, enhance assistive technologies, and expand the frontiers of brain-computer interaction.
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic coherence. Moreover, existing evaluation metrics overemphasize contextual forgetting while inadequately assessing response fluency and relevance. To address these challenges, we propose ReLearn, a data augmentation and fine-tuning pipeline for effective unlearning, along with a comprehensive evaluation framework. This framework introduces Knowledge Forgetting Rate (KFR) and Knowledge Retention Rate (KRR) to measure knowledge-level preservation, and Linguistic Score (LS) to evaluate generation quality. Our experiments show that ReLearn successfully achieves targeted forgetting while preserving high-quality output. Through mechanistic analysis, we further demonstrate how reverse optimization disrupts coherent text generation, while ReLearn preserves this essential capability. Code is available at https://github.com/zjunlp/unlearn.
Recent advancements in LLM-based multi-agent (LLM-MA) systems have shown promise, yet significant challenges remain in managing communication and refinement when agents collaborate on complex tasks. In this paper, we propose \textit{Talk Structurally, Act Hierarchically (TalkHier)}, a novel framework that introduces a structured communication protocol for context-rich exchanges and a hierarchical refinement system to address issues such as incorrect outputs, falsehoods, and biases. \textit{TalkHier} surpasses various types of SoTA, including inference scaling model (OpenAI-o1), open-source multi-agent models (e.g., AgentVerse), and majority voting strategies on current LLM and single-agent baselines (e.g., ReAct, GPT4o), across diverse tasks, including open-domain question answering, domain-specific selective questioning, and practical advertisement text generation. These results highlight its potential to set a new standard for LLM-MA systems, paving the way for more effective, adaptable, and collaborative multi-agent frameworks. The code is available https://github.com/sony/talkhier.
Knowledge Tracing (KT) aims to predict students' future performances based on their former exercises and additional information in educational settings. KT has received significant attention since it facilitates personalized experiences in educational situations. Simultaneously, the autoregressive modeling on the sequence of former exercises has been proven effective for this task. One of the primary challenges in autoregressive modeling for Knowledge Tracing is effectively representing the anterior (pre-response) and posterior (post-response) states of learners across exercises. Existing methods often employ complex model architectures to update learner states using question and response records. In this study, we propose a novel perspective on knowledge tracing task by treating it as a generative process, consistent with the principles of autoregressive models. We demonstrate that knowledge states can be directly represented through autoregressive encodings on a question-response alternate sequence, where model generate the most probable representation in hidden state space by analyzing history interactions. This approach underpins our framework, termed Alternate Autoregressive Knowledge Tracing (AAKT). Additionally, we incorporate supplementary educational information, such as question-related skills, into our framework through an auxiliary task, and include extra exercise details, like response time, as additional inputs. Our proposed framework is implemented using advanced autoregressive technologies from Natural Language Generation (NLG) for both training and prediction. Empirical evaluations on four real-world KT datasets indicate that AAKT consistently outperforms all baseline models in terms of AUC, ACC, and RMSE. Furthermore, extensive ablation studies and visualized analysis validate the effectiveness of key components in AAKT.
Large Language Models (LLMs) are vulnerable to adversarial prompt based injects. These injects could jailbreak or exploit vulnerabilities within these models with explicit prompt requests leading to undesired responses. In the context of investigating prompt injects, the challenge is the sheer volume of input prompts involved that are likely to be largely benign. This investigative challenge is further complicated by the semantics and subjectivity of the input prompts involved in the LLM conversation with its user and the context of the environment to which the conversation is being carried out. Hence, the challenge for AI security investigators would be two-fold. The first is to identify adversarial prompt injects and then to assess whether the input prompt is contextually benign or adversarial. For the first step, this could be done using existing AI security solutions like guardrails to detect and protect the LLMs. Guardrails have been developed using a variety of approaches. A popular approach is to use signature based. Another popular approach to develop AI models to classify such prompts include the use of NLP based models like a language model. However, in the context of conducting an AI security investigation of prompt injects, these guardrails lack the ability to aid investigators in triaging or assessing the identified input prompts. In this applied research exploration, we explore the use of a text generation capabilities of LLM to detect prompt injects and generate explanation for its detections to aid AI security investigators in assessing and triaging of such prompt inject detections. The practical benefit of such a tool is to ease the task of conducting investigation into prompt injects.
Evaluating the open-ended text generation of large language models (LLMs) is challenging because of the lack of a clear ground truth and the high cost of human or LLM-based assessments. We propose a novel benchmark that evaluates LLMs using n-gram statistics and rules, without relying on human judgement or LLM-as-a-judge approaches. Using 50 question and reference answer sets, we introduce three new metrics based on n-grams and rules: Fluency, Truthfulness, and Helpfulness. Our benchmark strongly correlates with GPT-4o-based evaluations while requiring significantly fewer computational resources, demonstrating its effectiveness as a scalable alternative for assessing LLMs' open-ended generation capabilities.
Token representations in high-dimensional latent spaces often exhibit redundancy, limiting computational efficiency and reducing structural coherence across model layers. Hierarchical latent space folding introduces a structured transformation mechanism that enforces a multi-scale organization within learned embeddings, refining representational compactness while preserving essential contextual distinctions. The proposed approach incorporates dynamic folding operations that iteratively adjust token embeddings through structured transformations, influencing both short-range and long-range dependencies in sequential processing tasks. Empirical evaluation demonstrates a reduction in representational variance across layers, contributing to more stable perplexity distributions and enhancing predictive confidence in text generation. The structured redistribution of attention head utilization leads to more efficient allocation of computational resources, particularly in deeper layers, where hierarchical refinements improve contextual abstraction. Comparative analysis of activation sparsity patterns suggests that hierarchical adjustments selectively reinforce critical pathways while reducing computational overhead in non-essential regions of the model. Statistical assessments of token reordering frequencies reveal that hierarchical modifications introduce subtle shifts in sequential dependencies, improving contextual alignment while maintaining syntactic correctness. Computational trade-offs associated with hierarchical folding introduce marginal increases in training time per epoch, yet empirical findings indicate that inference efficiency benefits from the structured representation adjustments. The results highlight the impact of hierarchical latent space folding on optimizing model performance through improved representation structuring and computational efficiency.
Contextual adaptation in token embeddings plays a central role in determining how well language models maintain coherence and retain semantic relationships over extended text sequences. Static embeddings often impose constraints on lexical flexibility, leading to suboptimal performance when faced with complex sentence structures or domain-specific terminology shifts. To address this limitation, a structured approach was developed for dynamically reconfiguring token embeddings through continuous geometric transformations, ensuring that representations evolved in response to evolving discourse structures. A manifold-based transformation mechanism was integrated to regulate lexical positioning, allowing embeddings to undergo controlled shifts while preserving linguistic relationships across varying textual contexts. Empirical evaluations demonstrated that embedding reconfiguration contributed to reductions in perplexity, improved lexical coherence, and enhanced sentence-level continuity, particularly in structured and domain-adaptive text generation tasks. Comparative analyses of embedding drift indicated that dynamically restructured representations maintained stronger contextual consistency, reducing misalignment in token dependencies while preserving fluency in language modeling outputs. Computational overhead assessments confirmed that while training complexity increased due to the iterative refinement of embeddings, inference remained efficient, ensuring practical feasibility for real-time generation. Evaluations across multiple datasets further demonstrated that dynamically modulated embeddings exhibited broader lexical diversity, reducing repetitive token patterns and enabling a more adaptable representation learning process.