While code large language models have demonstrated remarkable progress in code generation, the generated code often exhibits poor runtime efficiency, limiting its practical application in performance-sensitive scenarios. To address this limitation, we propose an efficiency-oriented reinforcement learning framework guided by a novel performance reward. Based on this framework, we take a deeper dive into the code efficiency problem, identifying then proposing methods to overcome key bottlenecks: (1) Dynamic exploration overcomes the static data constraints of offline fine-tuning, enabling the discovery of more efficient code implementations. (2) The error-insensitive reinforcement learning method and high-contrast efficiency signals are crucial for mitigating systematic errors and achieving effective optimization. (3) Online exploration is most effective when starting from a high-correctness baseline, as this allows for efficiency improvements without sacrificing accuracy. With these discoveries, we finally propose a two-stage tuning method, which achieves high and balanced performance across correctness and efficiency. The results of experiments show the effectiveness of the method, which improves code correctness by 10.18% and runtime efficiency by 7.75% on a 7B model, achieving performance comparable to much larger model.
论文检索
输入标题、作者或关键词，从 100,903 篇学术成果中精准定位
SCIR: A Self-Correcting Iterative Refinement Framework for Enhanced Information Extraction Based on Schema
PDF ↗Although Large language Model (LLM)-powered information extraction (IE) systems have shown impressive capabilities, current fine-tuning paradigms face two major limitations: high training costs and difficulties in aligning with LLM preferences. To address these issues, we propose a novel universal IE paradigm—the Self-Correcting Iterative Refinement (SCIR) framework—along with a Multi-task Bilingual (Chinese-English) Self-Correcting (MBSC) dataset containing over 100,000 entries. The SCIR framework achieves plug-and-play compatibility with existing LLMs and IE systems through its Dual-Path Self-Correcting module and feedback-driven optimization, thereby significantly reducing training costs. Concurrently, the MBSC dataset tackles the challenge of preference alignment by indirectly distilling GPT-4's capabilities into IE result detection models. Experimental results demonstrate that SCIR outperforms state-of-the-art IE methods across three key tasks— named entity recognition, relation extraction, and event extraction—achieving a 5.27 percent average improvement in span-based Micro-F1 while reducing training costs by 87 percent compared to baseline approaches. These advancements not only enhance the flexibility and accuracy of IE systems but also pave the way for lightweight and efficient IE paradigms.
Improving large language models (LLMs) for electronic health record (EHR) reasoning is essential for enabling accurate and generalizable clinical predictions. While LLMs excel at medical text understanding, they underperform on EHR-based prediction tasks due to challenges in modeling temporally structured, high-dimensional data. Existing approaches often rely on hybrid paradigms, where LLMs serve merely as frozen prior retrievers while downstream deep learning (DL) models handle prediction, failing to improve the LLM’s intrinsic reasoning capacity and inheriting the generalization limitations of DL models. To this end, we propose EAG-RL, a novel two-stage training framework designed to intrinsically enhance LLMs’ EHR reasoning ability through expert attention guidance, where expert EHR models refer to task-specific DL models trained on EHR data. Concretely, EAG-RL first constructs high-quality, stepwise reasoning trajectories using expert-guided Monte Carlo Tree Search to effectively initialize the LLM’s policy. Then, EAG-RL further optimizes the policy via reinforcement learning by aligning the LLM’s attention with clinically salient features identified by expert EHR models. Extensive experiments on two real-world EHR datasets show that EAG-RL improves the intrinsic EHR reasoning ability of LLMs by an average of 14.62%, while also enhancing robustness to feature perturbations and generalization to unseen clinical domains. These results demonstrate the practical potential of EAG-RL for real-world deployment in clinical prediction tasks.
RESTL: Reinforcement Learning Guided by Multi-Aspect Rewards for Signal Temporal Logic Transformation
PDF ↗Signal Temporal Logic (STL) is a powerful formal language for specifying real-time specifications of Cyber-Physical Systems (CPS). Transforming specifications written in natural language into STL formulas automatically has attracted increasing attention. Existing rule-based methods depend heavily on rigid pattern matching and domain-specific knowledge, limiting their generalizability and scalability. Recently, Supervised Fine-Tuning (SFT) of large language models (LLMs) has been successfully applied to transform natural language into STL. However, the lack of fine-grained supervision on atomic proposition correctness, semantic fidelity, and formula readability often leads SFT-based methods to produce formulas misaligned with the intended meaning. To address these issues, we propose RESTL, a reinforcement learning (RL)-based framework for the transformation from natural language to STL. RESTL introduces multiple independently trained reward models that provide fine-grained, multi-faceted feedback from four perspectives, i.e., atomic proposition consistency, semantic alignment, formula succinctness, and symbol matching. These reward models are trained with a curriculum learning strategy to improve their feedback accuracy, and their outputs are aggregated into a unified signal that guides the optimization of the STL generator via Proximal Policy Optimization (PPO). Experimental results demonstrate that RESTL significantly outperforms state-of-the-art methods in both automatic metrics and human evaluations.
Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments and diverse accents. To address this issue, test-time adaptation (TTA) has shown great potential in improving the model adaptability at inference time without ground-truth labels, and existing TTA methods often rely on pseudo-labeling or entropy minimization. However, by treating model confidence as a learning signal, these methods may reinforce high-confidence errors, leading to confirmation bias that undermines adaptation. To overcome these limitations, we present ASR-TRA, a novel Test-time Reinforcement Adaptation framework inspired by causal intervention. More precisely, our method introduces a learnable decoder prompt and utilizes temperature-controlled stochastic decoding to generate diverse transcription candidates. These are scored by a reward model that measures audio-text semantic alignment, and the resulting feedback is used to update both model and prompt parameters via reinforcement learning. Comprehensive experiments on LibriSpeech with synthetic noise and L2 Arctic accented English datasets demonstrate that our method significantly outperforms existing state-of-the-art (SOTA), including SUTA and SGEM, in both accuracy and inference speed. Ablation studies further confirm the effectiveness of combining audio and language-based rewards, highlighting our method's enhanced stability and interpretability. Overall, our approach provides a practical and robust solution for deploying ASR systems in challenging real-world conditions.
Verifying the complex and multi-step reasoning of Large Language Models (LLMs) is a critical challenge, as holistic methods often overlook localized flaws. Step-by-step validation is a promising alternative, yet existing methods are often rigid. They struggle to adapt to diverse reasoning structures, from formal proofs to informal natural language narratives. To address this adaptability gap, we propose the Graph of Verification (GoV), a novel framework for adaptable and multi-granular verification. GoV's core innovation is its flexible node block architecture. This mechanism allows GoV to adaptively adjust its verification granularity—from atomic steps for formal tasks to entire paragraphs for natural language—to match the native structure of the reasoning process. This flexibility allows GoV to resolve the fundamental trade-off between verification precision and robustness. Experiments on both well-structured and loosely-structured benchmarks demonstrate GoV's versatility. The results show that GoV's adaptive approach significantly outperforms both holistic baselines and other state-of-the-art decomposition-based methods, establishing a new standard for training-free reasoning verification.
GlitchCleaner: Lightweight Glitch Tokens Repairing by Lossless Gated LoRA in Large Language Models
PDF ↗Large language models (LLMs) have been increasingly applied across a wide range of domains. However, recent studies have identified the presence of certain glitch tokens in their vocabularies, which can trigger hallucinations and lead to unpredictable or even harmful outputs. While various methods have been proposed to detect such tokens, effectively repairing them remains a key challenge for ensuring the reliability of LLMs. In this work, we propose GlitchCleaner, a lightweight yet effective approach to mitigate the adverse effects caused by glitch tokens. GlitchCleaner introduces auxiliary branches into specific components within selected layers of the model, enabling efficient and targeted token repair. These branches are implemented using the low-rank adaptation (LoRA) technique, adding less than 0.1% additional parameters to the original model. Furthermore, a gating mechanism dynamically controls the activation of these branches based on the model’s input, ensuring precise intervention without disrupting normal inference behavior. Experimental results across multiple mainstream models demonstrate that our method achieves an average repair rate of 86.88%, representing an improvement of over 30% compared to existing approaches, while ensuring lossless preservation of the model’s baseline capabilities and causing negligible impact on inference speed.
SegMem-RAG: Adaptive Memory for Retrieval-Augmented Generation in Open-Ended Knowledge Environments
PDF ↗Retrieval-Augmented Generation (RAG) improves the factual accuracy of large language models by grounding responses in external content. However, most RAG systems assume access to static and well-organized corpora with fixed retrieval logic. In practice, real-world sources are heterogeneous and unlabeled, including user-uploaded documents, manuals, and datasets. Effective access in such settings requires adaptive and self-directed retrieval behavior. We present SegMem‑RAG, a memory-augmented RAG framework that learns to route queries across multiple unlabeled corpora based on experience. It incrementally updates a structured memory and uses self-reflection to guide retrieval over time without supervision. Experimental results demonstrate that SegMem‑RAG significantly outperforms recent baselines in generation quality on multi-corpus QA tasks.
MHA2MLA-VLM: Enabling DeepSeek’s Economical Multi-Head Latent Attention Across Vision-Language Models
PDF ↗As vision-language models (VLMs) tackle increasingly complex and multimodal tasks, the rapid growth of Key-Value (KV) cache imposes significant memory and computational bottlenecks during inference. While Multi-Head Latent Attention (MLA) offers an effective means to compress the KV cache and accelerate inference, adapting existing VLMs to the MLA architecture without costly pretraining remains largely unexplored. In this work, we present \textbf{MHA2MLA-VLM}, a parameter-efficient and multimodal-aware framework for converting off-the-shelf VLMs to MLA. Our approach features two core techniques: (1) a modality-adaptive partial-RoPE strategy that supports both traditional and multimodal settings by selectively masking nonessential dimensions, and (2) a modality-decoupled low-rank approximation method that independently compresses the visual and textual KV spaces. Furthermore, we introduce parameter-efficient fine-tuning to minimize adaptation cost and demonstrate that minimizing output activation error, rather than parameter distance, substantially reduces performance loss. Extensive experiments on three representative VLMs show that MHA2MLA-VLM restores original model performance with minimal supervised data, significantly reduces KV cache footprint, and integrates seamlessly with KV quantization.
Speech-language models (SLMs) offer a promising path toward unifying speech and text understanding and generation. However, challenges remain in achieving effective cross-modal alignment and high-quality speech generation. In this work, we systematically investigate the role of speech tokenizer designs in LLM-centric SLMs, augmented by speech heads and speaker modeling. We compare coupled, semi-decoupled, and fully decoupled speech tokenizers under a fair SLM framework and find that decoupled tokenization significantly improves alignment and synthesis quality. To address the information density mismatch between speech and text, we introduce multi-token prediction (MTP) into SLMs, enabling each hidden state to decode multiple speech tokens. This leads to up to 12× faster decoding and a substantial drop in word error rate (from 6.07 to 3.01). Furthermore, we propose a speaker-aware generation paradigm and introduce RoleTriviaQA, a large-scale role-playing knowledge QA benchmark with diverse speaker identities. Experiments demonstrate that our methods enhance both knowledge understanding and speaker consistency.
Large Language Models (LLMs) are increasingly deployed in time-critical systems, such as robotics, autonomous driving, embodied intelligence, and industrial automation, where generating accurate responses within a given time budget is crucial for decision-making, control, or safety-critical tasks. However, the auto-regressive generation process of LLMs makes it challenging to model and estimate the end-to-end execution time. Furthermore, existing efficient inference methods based on a fixed key-value (KV) cache eviction ratio struggle to adapt to varying tasks with diverse time budgets, where an improper eviction ratio may lead to incomplete inference or a drop in response performance. In this paper, we propose TimeBill, a novel time-budgeted inference framework for LLMs that balances the inference efficiency and response performance. To be more specific, we propose a fine-grained response length predictor (RLP) and an execution time estimator (ETE) to accurately predict the end-to-end execution time of LLMs. Following this, we develop a time-budgeted efficient inference approach that adaptively adjusts the KV cache eviction ratio based on execution time prediction and the given time budget. Finally, through extensive experiments, we demonstrate the advantages of TimeBill in improving task completion rate and maintaining response performance under various overrun strategies.
Graph Neural Networks (GNNs) offer superior modeling capabilities for text classification by capturing complex spatial features within semantic representations. However, existing graph-based approaches often suffer from computational inefficiency and limited ability to model both fine-grained local structures and the sequential nature of text. To address these challenges, we propose HC2-GNN, a Hierarchical Clustering and Coarsening Graph Neural Network, which introduces a novel lightweight graph clustering algorithm called Compromise Conductance Graph Clustering (C2GC). C2GC enables efficient graph clustering while simultaneously preserving both the textual order and the topological coherence of subgraphs. Furthermore, it incorporates a virtue cluster mechanism that expands each subgraph with semantically relevant neighbors, explicitly enabling cross-cluster information propagation without compromising local structural integrity. HC2-GNN aggregates local and global features by combining subgraph-level and full-graph representations, enhancing semantic discriminability for classification. Extensive experiments on benchmark datasets demonstrate that HC2-GNN consistently outperforms existing state-of-the-art text classification methods.
Neuro-symbolic learning has emerged as a promising paradigm for interpretable visual reasoning, where mapping natural language questions to executable programs plays a central role. However, most existing methods focus exclusively on the forward program generation from questions while overlooking the reverse process of reconstructing questions from programs. In this paper, we propose BiPaR (Bidirectional Parsing and Reconstruction), a Transformer-based framework that jointly models both program parsing and question reconstruction within a unified architecture. Unlike previous approaches that only perform forward parsing, BiPaR introduces reverse program-to-question reconstruction as a powerful auxiliary signal, which improves program generation quality and accelerates convergence, particularly under limited supervision. We further provide a theoretical analysis showing how reverse reconstruction facilitates faster optimization during training. The bidirectional modeling makes BiPaR well-suited for both supervised and semi-supervised learning scenarios. We present two architectural variants: BiPaR-Full, which employs encoder-decoder Transformers for both modules; and BiPaR-DOnly, a lightweight variant that employs a decoder-only structure for question reconstruction, reducing model complexity. Experiments on CLEVR and a GQA subset demonstrate that BiPaR significantly outperforms standard Transformer baselines. Furthermore, in the semi-supervised learning setting, BiPaR achieves notable improvements by leveraging additional questions without program annotations.
Graphical User Interface (GUI) grounding, the task of mapping natural language instructions to precise screen coordinates, is fundamental to autonomous GUI agents. While existing methods achieve strong performance through extensive supervised training or reinforcement learning with labeled rewards, they remain constrained by the cost and availability of pixel-level annotations. We observe that when models generate multiple predictions for the same GUI element, the spatial overlap patterns reveal implicit confidence signals that can guide more accurate localization. Leveraging this insight, GUI-RC (Region Consistency), a test-time scaling method that constructs spatial voting grids from multiple sampled predictions to identify consensus regions where models show highest agreement. Without any training, GUI-RC improves accuracy by 2-3% across various architectures on ScreenSpot benchmarks. We further introduce GUI-RCPO (Region Consistency Policy Optimization), transforming these consistency patterns into rewards for test-time reinforcement learning. By computing how well each prediction aligns with the collective consensus, GUI-RCPO enables models to iteratively refine their outputs on unlabeled data during inference. Extensive experiments demonstrate the generality of our approach: using only 1,272 unlabeled data, GUI-RCPO achieves 3-6% accuracy improvements across various architectures on ScreenSpot benchmarks. Our approach reveals the untapped potential of test-time scaling and test-time reinforcement learning for GUI grounding, offering a promising path toward more data-efficient GUI agents.
Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods prioritise semantic similarity over task intent, degrading multi-session coherence. We propose MemGuide, a two-stage intent-driven memory selection framework: (1) Intent‑Aligned Retrieval retrieves goal-consistent QA‑formatted memory units; (2) Missing‑Slot Guided Filtering reranks units by slot-completion gain via a chain‑of‑thought reasoner and fine‑tuned LLaMA‑8B filter. We also introduce the MS-TOD, the first multi-session TOD benchmark with 132 diverse personas, 956 task goals, and annotated intent-aligned memory targets. Evaluations on MS-TOD show that MemGuide boosts task success rate by 11% (88%→99%) and reduces dialogue length by 2.84 turns, and matches single‑session performance.
As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. However, existing benchmarks for evaluating the reliability of Multimodal Large Language Models (MLLMs) predominantly focus on textual or visual modalities with a primary emphasis on English, which creates a gap in evaluation when processing multilingual input, especially in speech. To bridge this gap, we propose a novel Cross-lingual and Cross-modal Factuality benchmark (CCFQA). Specifically, the CCFQA benchmark contains parallel speech-text factual questions across 8 languages, designed to systematically evaluate MLLMs' cross-lingual and cross-modal factuality capabilities. Our experimental results demonstrate that current MLLMs still face substantial challenges on the CCFQA benchmark. Furthermore, we propose a few-shot transfer learning strategy that effectively transfers the Question Answering (QA) capabilities of LLMs in English to multilingual Spoken Question Answering (SQA) tasks, achieving competitive performance with GPT-4o-mini-Audio using just 5-shot training. We release CCFQA as a foundational research resource to promote the development of MLLMs with more robust and reliable speech understanding capabilities.
High-quality instructions are crucial for aligning pretrained models to improve their performance on downstream tasks. Although current instruction datasets have reached tens of millions of samples, models finetuned on them may still struggle with complex instruction following and tasks in rare domains. This is primarily due to limited expansion in both "coverage" (coverage of task types and knowledge areas) and "depth" (instruction complexity) of the instruction set. To address this issue, we propose a systematic instruction data construction framework, which integrates a hierarchical labeling system, an informative seed selection algorithm, an evolutionary data synthesis process, and a model deficiency diagnosis with targeted data generation. These components form an iterative closed-loop to continuously enhance the coverage and depth of instruction data. Based on this framework, we construct Infinity Instruct Subject, a high-quality dataset containing approximately 1.5 million instructions. Experiments on multiple foundation models and benchmark tasks demonstrate its effectiveness in improving instruction-following capabilities. Further analyses suggest that InfinityInstruct-Subject shows enlarged coverage and depth compared to comparable synthesized instruction datasets.
Multi-Hop Question Answering (MHQA) requires step-by-step reasoning across multiple pieces of information to answer complex questions. The cache-aided Retrieval-Augmented Generation (RAG) can accelerate the process of external knowledge retrieval at each reasoning step for MHQA. However, existing methods focus on the internal structure and ignore the misalignment between the queries’ arrival order and cache hit order. To tackle this, we propose Mnemosyne, a cache hit order fitting method designed to accelerate the RAG progress for MHQA. Specifically, our cache-aware order fitting strategy adjusts the order of queries arrival via graph reordering to better align with the cache hit order, thereby reducing the likelihood of failed or unproductive retrieval attempts. The multi-granularity caching storage mechanism is designed to loosen the strict hit condition to multiple similar semantic matching modes, facilitating that relevant documents can still be retrieved. Experiments conducted on four multi-hop QA datasets demonstrate that Mnemosyne effectively reduces retrieval latency while enhancing task answer F1 score, achieving a superior trade-off between efficiency and effectiveness.
TO-GATE: Clarifying Questions and Summarizing Responses with Trajectory Optimization for Eliciting Human Preference
PDF ↗Humans increasingly query Large Language Models (LLMs) to accomplish personal tasks according to their individual preferences. However, these preferences are often unconsciously veiled during conversation. To address this, LLMs have to elicit human preferences through multi-turn dialogue, where tasks are accomplished via iterative clarifying questions and final response generated by LLMs as effective questioners. Existing approaches based on self-taught reasoning have two limitations: 1) they struggle to avoid generating irrelevant questions and 2) the final responses to tasks are misled by the conversations. To overcome these limitations, we propose TO-GATE, a novel framework that enhances question generation through trajectory optimization. TO-GATE comprises two key components: a clarification resolver, which generates optimal questioning trajectories to produce effective elicitation questions, and a summarizer, which ensures task-aligned final responses. Experimental results show that TO-GATE significantly outperforms baseline methods, achieving a 9.32% improvement on standard preference elicitation benchmarks.
SACodec: Asymmetric Quantization with Semantic Anchoring for Low-Bitrate High-Fidelity Neural Speech Codecs
PDF ↗Neural Speech Codecs face a fundamental trade-off at low bitrates: preserving acoustic fidelity often compromises semantic richness. To address this, we introduce SACodec, a novel codec built upon an asymmetric dual-quantizer that employs our proposed Semantic Anchoring mechanism. This design strategically decouples the quantization of Semantic and Acoustic details. The semantic anchoring is achieved via a lightweight projector that aligns acoustic features with a frozen, large-scale mHuBERT codebook, injecting linguistic priors while guaranteeing full codebook utilization. Sequentially, for acoustic details, a residual activation module with SimVQ enables a single-layer quantizer (acoustic path) to faithfully recover fine-grained information. At just 1.5 kbps, SACodec establishes a new state of the art by excelling in both fidelity and semantics: subjective listening tests confirm that its reconstruction quality is perceptually highly comparable to ground-truth audio, while its tokens demonstrate substantially improved semantic richness in downstream tasks. This work suggests that assigning specialized semantic quantizers to distinct information streams offers an effective path to reconcile the long-standing trade-off between fidelity, semantics, and modeling simplicity in low-bitrate speech tokenization.