University of Louisiana at Lafayette, USA
Abstract:Large language models (LLMs) have recently achieved notable success in code-generation benchmarks such as HumanEval and LiveCodeBench. However, a detailed examination reveals that these evaluation suites often comprise only a limited number of homogeneous test cases, resulting in subtle faults going undetected. This not only artificially inflates measured performance but also compromises accurate reward estimation in reinforcement learning frameworks utilizing verifiable rewards (RLVR). To address these critical shortcomings, we systematically investigate the test-case generation (TCG) task by proposing multi-dimensional metrics designed to rigorously quantify test-suite thoroughness. Furthermore, we introduce a human-LLM collaborative method (SAGA), leveraging human programming expertise with LLM reasoning capability, aimed at significantly enhancing both the coverage and the quality of generated test cases. In addition, we develop a TCGBench to facilitate the study of the TCG task. Experiments show that SAGA achieves a detection rate of 90.62% and a verifier accuracy of 32.58% on TCGBench. The Verifier Accuracy (Verifier Acc) of the code generation evaluation benchmark synthesized by SAGA is 10.78% higher than that of LiveCodeBench-v6. These results demonstrate the effectiveness of our proposed method. We hope this work contributes to building a scalable foundation for reliable LLM code evaluation, further advancing RLVR in code generation, and paving the way for automated adversarial test synthesis and adaptive benchmark integration.
Abstract:Large language models (LLMs) have achieved remarkable progress in code generation, yet their true programming competence remains underexplored. We introduce the Code Triangle framework, which systematically evaluates LLMs across three fundamental dimensions: editorial analysis, code implementation, and test case generation. Through extensive experiments on competitive programming benchmarks, we reveal that while LLMs can form a self-consistent system across these dimensions, their solutions often lack the diversity and robustness of human programmers. We identify a significant distribution shift between model cognition and human expertise, with model errors tending to cluster due to training data biases and limited reasoning transfer. Our study demonstrates that incorporating human-generated editorials, solutions, and diverse test cases, as well as leveraging model mixtures, can substantially enhance both the performance and robustness of LLMs. Furthermore, we reveal both the consistency and inconsistency in the cognition of LLMs that may facilitate self-reflection and self-improvement, providing a potential direction for developing more powerful coding models.
Abstract:Scaling law builds the relationship between training computation and validation loss, enabling researchers to effectively predict the loss trending of models across different levels of computation. However, a gap still remains between validation loss and the model's downstream capabilities, making it untrivial to apply scaling law to direct performance prediction for downstream tasks. The loss typically represents a cumulative penalty for predicted tokens, which are implicitly considered to have equal importance. Nevertheless, our studies have shown evidence that when considering different training data distributions, we cannot directly model the relationship between downstream capability and computation or token loss. To bridge the gap between validation loss and downstream task capabilities, in this work, we introduce Capability Salience Vector, which decomposes the overall loss and assigns different importance weights to tokens to assess a specific meta-capability, aligning the validation loss with downstream task performance in terms of the model's capabilities. Experiments on various popular benchmarks demonstrate that our proposed Capability Salience Vector could significantly improve the predictability of language model performance on downstream tasks.
Abstract:We propose a novel framework for comprehending the reasoning capabilities of large language models (LLMs) through the perspective of meta-learning. By conceptualizing reasoning trajectories as pseudo-gradient descent updates to the LLM's parameters, we identify parallels between LLM reasoning and various meta-learning paradigms. We formalize the training process for reasoning tasks as a meta-learning setup, with each question treated as an individual task, and reasoning trajectories serving as the inner loop optimization for adapting model parameters. Once trained on a diverse set of questions, the LLM develops fundamental reasoning capabilities that can generalize to previously unseen questions. Extensive empirical evaluations substantiate the strong connection between LLM reasoning and meta-learning, exploring several issues of significant interest from a meta-learning standpoint. Our work not only enhances the understanding of LLM reasoning but also provides practical insights for improving these models through established meta-learning techniques.
Abstract:We introduce KoLasSimpleQA, the first benchmark evaluating the multilingual factual ability of Large Language Models (LLMs). Inspired by existing research, we created the question set with features such as single knowledge point coverage, absolute objectivity, unique answers, and temporal stability. These questions enable efficient evaluation using the LLM-as-judge paradigm, testing both the LLMs' factual memory and self-awareness ("know what they don't know"). KoLasSimpleQA expands existing research in two key dimensions: (1) Breadth (Multilingual Coverage): It includes 9 languages, supporting global applicability evaluation. (2) Depth (Dual Domain Design): It covers both the general domain (global facts) and the language-specific domain (such as history, culture, and regional traditions) for a comprehensive assessment of multilingual capabilities. We evaluated mainstream LLMs, including traditional LLM and emerging Large Reasoning Models. Results show significant performance differences between the two domains, particularly in performance metrics, ranking, calibration, and robustness. This highlights the need for targeted evaluation and optimization in multilingual contexts. We hope KoLasSimpleQA will help the research community better identify LLM capability boundaries in multilingual contexts and provide guidance for model optimization. We will release KoLasSimpleQA at https://github.com/opendatalab/KoLasSimpleQA .
Abstract:Recent advancements in generative artificial intelligence have introduced groundbreaking approaches to innovating next-generation semantic communication, which prioritizes conveying the meaning of a message rather than merely transmitting raw data. A fundamental challenge in semantic communication lies in accurately identifying and extracting the most critical semantic information while adapting to downstream tasks without degrading performance, particularly when the objective at the receiver may evolve over time. To enable flexible adaptation to multiple tasks at the receiver, this work introduces a novel semantic communication framework, which is capable of jointly capturing task-specific information to enhance downstream task performance and contextual information. Through rigorous experiments on popular image datasets and computer vision tasks, our framework shows promising improvement compared to existing work, including superior performance in downstream tasks, better generalizability, ultra-high bandwidth efficiency, and low reconstruction latency.
Abstract:Semantic communications represent a new paradigm of next-generation networking that shifts bit-wise data delivery to conveying the semantic meanings for bandwidth efficiency. To effectively accommodate various potential downstream tasks at the receiver side, one should adaptively convey the most critical semantic information. This work presents a novel task-adaptive semantic communication framework based on diffusion models that is capable of dynamically adjusting the semantic message delivery according to various downstream tasks. Specifically, we initialize the transmission of a deep-compressed general semantic representation from the transmitter to enable diffusion-based coarse data reconstruction at the receiver. The receiver identifies the task-specific demands and generates textual prompts as feedback. Integrated with the attention mechanism, the transmitter updates the semantic transmission with more details to better align with the objectives of the intended receivers. Our test results demonstrate the efficacy of the proposed method in adaptively preserving critical task-relevant information for semantic communications while preserving high compression efficiency.
Abstract:In a distributed mixture-of-experts (MoE) system, a server collaborates with multiple specialized expert clients to perform inference. The server extracts features from input data and dynamically selects experts based on their areas of specialization to produce the final output. Although MoE models are widely valued for their flexibility and performance benefits, adapting distributed MoEs to operate effectively in wireless networks has remained unexplored. In this work, we introduce a novel channel-aware gating function for wireless distributed MoE, which incorporates channel conditions into the MoE gating mechanism. To train the channel-aware gating, we simulate various signal-to-noise ratios (SNRs) for each expert's communication channel and add noise to the features distributed to the experts based on these SNRs. The gating function then utilizes both features and SNRs to optimize expert selection. Unlike conventional MoE models which solely consider the alignment of features with the specializations of experts, our approach additionally considers the impact of channel conditions on expert performance. Experimental results demonstrate that the proposed channel-aware gating scheme outperforms traditional MoE models.
Abstract:We introduce OpenHuEval, the first benchmark for LLMs focusing on the Hungarian language and specifics. OpenHuEval is constructed from a vast collection of Hungarian-specific materials sourced from multiple origins. In the construction, we incorporated the latest design principles for evaluating LLMs, such as using real user queries from the internet, emphasizing the assessment of LLMs' generative capabilities, and employing LLM-as-judge to enhance the multidimensionality and accuracy of evaluations. Ultimately, OpenHuEval encompasses eight Hungarian-specific dimensions, featuring five tasks and 3953 questions. Consequently, OpenHuEval provides the comprehensive, in-depth, and scientifically accurate assessment of LLM performance in the context of the Hungarian language and its specifics. We evaluated current mainstream LLMs, including both traditional LLMs and recently developed Large Reasoning Models. The results demonstrate the significant necessity for evaluation and model optimization tailored to the Hungarian language and specifics. We also established the framework for analyzing the thinking processes of LRMs with OpenHuEval, revealing intrinsic patterns and mechanisms of these models in non-English languages, with Hungarian serving as a representative example. We will release OpenHuEval at https://github.com/opendatalab/OpenHuEval .
Abstract:Semantic communication marks a new paradigm shift from bit-wise data transmission to semantic information delivery for the purpose of bandwidth reduction. To more effectively carry out specialized downstream tasks at the receiver end, it is crucial to define the most critical semantic message in the data based on the task or goal-oriented features. In this work, we propose a novel goal-oriented communication (GO-COM) framework, namely Goal-Oriented Semantic Variational Autoencoder (GOS-VAE), by focusing on the extraction of the semantics vital to the downstream tasks. Specifically, we adopt a Vector Quantized Variational Autoencoder (VQ-VAE) to compress media data at the transmitter side. Instead of targeting the pixel-wise image data reconstruction, we measure the quality-of-service at the receiver end based on a pre-defined task-incentivized model. Moreover, to capture the relevant semantic features in the data reconstruction, imitation learning is adopted to measure the data regeneration quality in terms of goal-oriented semantics. Our experimental results demonstrate the power of imitation learning in characterizing goal-oriented semantics and bandwidth efficiency of our proposed GOS-VAE.