Research on ancient Chinese language is of great significance for tracing Chinese history and civilization. In the field of large language models, studies on the pre-Qin excavated documents such as Oracle Bone Inscriptions, Bronze Inscriptions, and Bamboo Book of Chu remain insufficient. This is because these ancient characters have a low level of digitization, training corpora are extremely scarce, and they typically contain complex and rich semantic information. Therefore, we propose an ancient character semantic-aware embedding for large language models. This embedding integrates both the glyph and lexicality of ancient characters and maps them to the modern Chinese semantic space. We also design a two-stage method for lightweight and parameter-efficient training of the embedding. Finally, we conduct extensive experiments on excavated documents from the pre-Qin period, and the results demonstrate the effectiveness of our approach.
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
Logical Structure as Knowledge: Enhancing LLM Reasoning via Structured Logical Knowledge Density Estimation
PDF ↗The reasoning capabilities of Large Language Models (LLMs) are increasingly attributed to training data quality rather than mere parameter scaling. However, existing data-centric paradigms often equate quality with factuality or diversity and ignore the internal logical complexity of training samples. In this work, we propose that natural language harbors Structured Logical Knowledge manifested through entailment relationships and logical topologies. To quantify this, we introduce Structured Logical Knowledge Density (SLKD), a novel metric that measures logical information content by decomposing natural language into executable predicates and logical primitives. Our analysis reveals a significant logical disparity in current datasets where sparse logical signals predominate. Consequently, we propose a density-aware re-cognizing optimization strategy that prioritizes high-density logical samples to align training with the model’s reasoning boundary. Extensive experiments demonstrate that our approach enhances reasoning performance and generalization without increasing total data volume. These results, further validated within a reinforcement learning framework, suggest that elevating logical density is more critical than expanding data scale for realizing the full cognitive potential of LLMs. The anonymized code is available in the Appendix C.
Candidate-Aware Retrieval and Reranking for Multiple-Choice Question Answering: Arabic as a Case Study
PDF ↗Large language models (LLMs) have recently achieved impressive results on multiple-choice question answering (MCQA), with retrieval-augmented generation (RAG) emerging as an effective strategy for improving the performance of smaller models. However, existing RAG formulations face persistent challenges: retrieving too many passages often introduces noise, and even when relevant content is retrieved, models may still struggle with partially relevant or conflicting information. Moreover, while LLMs perform strongly on English benchmarks, their accuracy declines substantially on Arabic multi-task evaluations, revealing ongoing issues in cross-lingual transfer and domain adaptation. In this paper, we propose a novel approach, using Arabic as a representative case study, that jointly models the relevance of both the question and its candidate answers when selecting contextual passages. The method employs a lightweight reranker trained with a hybrid regression–triplet loss objective to identify passages that provide discriminative and reliable evidence. Extensive experiments across multiple model sizes and humanities domains show that our approach consistently outperforms both standard RAG baselines and reranker baselines, delivering two- to threefold improvements while remaining competitive with considerably larger models.
CGBridge: Bridging Code Graphs and Large Language Models for Better Structure-Aware Code Understanding
PDF ↗Large Language Models (LLMs) have demonstrated remarkable performance in code intelligence tasks such as code generation, summarization, and translation. However, their reliance on linearized token sequences makes them brittle to long-range program dependencies and superficial lexical shifts such as identifier renaming. Existing structure-aware approaches typically treat structure as serialized text prompts or auxiliary training objectives, which often inflate context length or rely on internalized structural priors, failing to provide explicit guidance during inference. To address these limitations, we propose CGBridge, a novel plug-and-play method that enhances LLMs with Code Graph information through an external, trainable Bridge module. It aligns Code Property Graph structure with code semantics and compresses them into compact soft-prefixes, decoupling structural reasoning from textual generation without updating the backbone. Experiments across multiple code LLM backbones and scales show consistent gains over both text-only adaptation and graph-augmented baselines. Furthermore, CGBridge remains robust under identifier renaming and enables over 4× faster inference than LoRA-tuned models, demonstrating both effectiveness and efficiency in structure-aware code understanding.
Text-to-image (T2I) generative models have achieved remarkable progress, demonstrating exceptional capability in synthesizing high-quality images from textual prompts. While existing research and benchmarks have extensively evaluated the ability of T2I models to follow the literal meaning of prompts, their ability to reason over prompts with domain knowledge to uncover implicit meaning and contextual nuances remains underexplored. To bridge this gap, we introduce T2I-ReasonBench, a novel benchmark designed to explore the knowledge-driven reasoning capabilities of T2I models.T2I-ReasonBench comprises 800 meticulously designed prompts organized into four dimensions: (1) Idiom Interpretation, (2) Textual Image Design, (3) Entity Reasoning, and (4) Scientific Reasoning. These dimensions challenge models to integrate domain knowledge, infer implicit meaning, and resolve contextual ambiguities. To quantify the performance, we introduce a two-stage evaluation framework: a large language model (LLM) generates prompt-specific question-criterion pairs that evaluate if the image includes the essential elements resulting from correct reasoning; a multimodal LLM (MLLM) then scores the generated image against these criteria. Our comprehensive study across 16 state-of-the-art diffusion and unified multimodal models (UMMs) reveal two primary bottlenecks. First, many models lack the foundational reasoning ability to fully comprehend complex prompts. Second, even models with stronger reasoning modules exhibit a persistent gap between their internal understanding and the final generated image. This highlights an urgent need for the next generation of T2I systems to not only improve their reasoning capability but also to enhance integration between reasoning and synthesis.
PBEBench: A Multi-Step Programming by Examples Reasoning Benchmark inspired by Historical Linguistics
PDF ↗While many benchmarks evaluate the reasoning abilities of Large Language Models (LLMs), few isolate reasoning as a capability independent of domain knowledge. We introduce a new benchmark for inductive reasoning inspired by Sound Law Induction (SLI) in historical linguistics and formulated in a simple multi-step Programming by Example (PBE) framework. The task requires inducing a cascade of string rewrite programs that transform inputs into target outputs. We present PBEBench, a fully automated evaluation approach that generates such problems with controllable difficulty and ordering constraints, enabling scalable and contamination-resistant evaluation of sequential inductive reasoning. Using this approach, we construct three datasets that show a large gap between models that leverage test-time compute or long chain-of-thought reasoning and those that do not. Although recent models such as GPT-5 and gpt-oss-120b show promise, solve rates remain below 5% on hard PBEBench instances with long program cascades, even under computationally expensive scaling strategies. Finally, we show that PBEBench scores are more predictive of performance on real SLI than are other inductive reasoning benchmarks. We will release code and data to support further research.
Teacher sentiment analysis is pivotal for understanding instructional dynamics, yet it remains challenging because classroom expressions are professionally regulated performances rather than spontaneous outbursts. However, existing approaches typically treat sentiment as a static, monolithic label, failing to capture this structured heterogeneity. To effectively model this complexity, we decompose teacher sentiment into three granularities: coarse-level performativity, medium-level intra-class heterogeneity, and fine-level cross-modal complementarity. Guided by this perspective, we propose CF-TSA, a coarse-to-fine multimodal framework. Specifically, we employ CLS-guided cross-modal attention to recover effective signals from regulated displays (coarse-level), thresholded substyle discovery to identify latent pedagogical styles (medium-level), and substyle-aware contrastive learning to align dynamic multimodal cue compositions (fine-level). Experiments on T-MED and CMU-MOSEI demonstrate that CF-TSA consistently outperforms state-of-the-art baselines, validating the effectiveness of the coarse-to-fine perspective and the hierarchical modeling.
Cogito: A Cognitive Agentic Framework Driven by Dynamic Graph of Thoughts for Financial Report Generation
PDF ↗Financial report generation is a complex task that requires gathering and reasoning over multi-source information. Recent advances in Large Language Models have made them a promising solution for automating this process. However, the reasoning paths in traditional Chain-of-Thought paradigms are inherently constrained by predefined, static computational topologies, rendering them ill-equipped to handle the dynamic uncertainties of real-world financial environments. To tackle this challenge, we propose Cogito, a cognitively grounded agentic framework for professional financial report generation. At its core, Cogito is driven by Dynamic Graph of Thoughts, a novel reasoning mechanism that models the agent’s reasoning process as an evolving topology for adaptive exploration.We further introduce a Social Collaboration Mechanism to facilitate coordinated agent interaction. Finally, Cogito is instantiated as a multi-agent system, where four specialized agents collaboratively execute the end-to-end report generation task. Extensive experiments on enterprise- and industry-level financial report generation benchmarks demonstrate the superiority of Cogito in data quality, analytical validity, and presentation quality.
The integration of large language models (LLMs) into a wide range of applications has highlighted the critical role of well-crafted system prompts, which require extensive testing and domain expertise. These prompts enhance task performance but may also encode sensitive information and filtering criteria, posing security risks if exposed. Recent research shows that system prompts are vulnerable to extraction attacks, while existing defenses are either easily bypassed or require constant updates to address new threats. In this work, we introduce ProxyPrompt, a novel defense mechanism that prevents prompt leakage by replacing the original prompt with a proxy. This proxy maintains the original task’s utility while obfuscating the extracted prompt, ensuring attackers cannot reproduce the task or access sensitive information. Comprehensive evaluations on 264 LLM and system prompt pairs show that ProxyPrompt protects 94.70% of prompts from extraction attacks, outperforming the next-best defense, which only achieves 42.80%.
Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text quality as sequence length increases. To address these limitations, we propose \textit{SuperWriter}-Agent, an agent-based framework designed to enhance the quality and consistency of long-form text generation. \textit{SuperWriter}-Agent introduces explicit structured thinking-through planning and refinement stages—into the generation pipeline, guiding the model to follow a more deliberate and cognitively grounded process akin to that of a professional writer. Based on this framework, we construct a supervised fine-tuning dataset to train a 7B \textit{SuperWriter}-LM. We further develop a hierarchical Direct Preference Optimization (DPO) procedure that uses Monte Carlo Tree Search (MCTS) to propagate final quality assessments and optimize each generation step accordingly. Empirical results across diverse benchmarks demonstrate that \textit{SuperWriter}-LM achieves state-of-the-art performance, surpassing even larger-scale baseline models in both automatic evaluation and human evaluation. Furthermore, comprehensive ablation studies demonstrate the effectiveness of hierarchical DPO and underscore the value of incorporating structured thinking steps to improve the quality of long-form text generation.
Do frontier LLMs reason causally, or do they pattern-match, yielding under pressure and hedging under uncertainty? We frame causal judgment as evaluation along three axes, Utility, Safety, and Wise Refusal, across Pearl’s Ladder. We introduce Recursive Causal Audit (RCA), a process-integrity evaluator whose Judge has no access to gold labels: it checks whether a model’s answer is entailed by itsown derivation, internally consistent, and not dominated by user hints under pressure. RCA unifies persona and pressure: prompt tone is the intervention that regulates pressure-induced drift. For fine diagnostic resolution we use CAUSALT3, with explicit trap families and standardized pressure protocols. CAUSALT3 reveals a Skepticism Trap (Claude Haiku rejects 60% of valid L1 links) and a Scaling Paradox (GPT-5.2 underperforms GPT-4-Turbo by 55 points on L3, driven by paralysis rather than hallucination). Under RCA, operating points shift toward the high-Utility, high-Safety quadrant without retraining, consistent with much of the observed failure arising from how answers are rendered under pressure rather than from missing causal knowledge.
TopoSHIELD: Reshaping the Flow of Malice via Spatio-Temporal Risk-Aware Topological Evolution in Multi-Agent Systems
PDF ↗While LLM-based Multi-Agent Systems (MAS) demonstrate remarkable problem-solving capabilities, their interconnectivity acts as a conduit for the rapid spread of malicious injections. Addressing the limitations of static defenses, we present TopoSHIELD, a framework that reshapes the flow of malice via risk-aware topological evolution. Our approach utilizes a spatio-temporal graph neural network to monitor interaction dynamics, calculating node risk entropy (NRE) and edge attack conductivity (EAC) to pinpoint vulnerabilities. Guided by these metrics, TopoSHIELD executes precise structural interventions, pruning high-risk edges and isolating compromised communities to block attack diffusion. Empirically, TopoSHIELD reduces toxicity by 58% on GPT-4o while preserving high utility (>90% success rate), outperforming existing baselines in both suppression efficiency and scalability.
Multimodal large language models excel at vision-language tasks but remain prone to hallucinations that undermine their reliability. Existing approaches predominantly treat hallucinations as classification errors, overlooking the heterogeneous behaviors of attention heads and their dynamic influences during inference. We revisit MLLM reasoning from an energy perspective and identify that hallucinations stem from imbalances between visual potential and language prior potential: when visual information is ambiguous or language priors dominate, attention heads tend to be driven by linguistic statistical patterns, generating content inconsistent with visual evidence. We propose AHEAD, a framework that quantifies the energetic properties of each attention head during object generation through two potential networks—the Visual Grounding Potential Network and the Language Prior Potential Network—and dynamically adjusts their contributions at inference time. Specifically, we amplify attention heads with strong visual grounding capacity while suppressing those overly reliant on language priors. Experiments across multiple benchmarks demonstrate that AHEAD significantly reduces hallucination rates without fine-tuning the base MLLM while maintaining generation quality.
As Large Language Models asymptotically approach human-level fluency in natural language generation, solely relying on surface-level semantic artifacts for detecting LLM-generated texts has become increasingly precarious. Existing detectors often falter when facing three critical challenges: adversarial perturbations, cross-domain shifts, and the rapid temporal evolution of the foundation model. To address these issues, we propose , a novel framework that reformulates text detection as a signal processing task within the time-frequency domain. Unlike previous methods that analyze static token probability distributions, models the generated output as a probability signal, upon which a differentiable Continuous Wavelet Transform is applied to convert them into learnable spectral representations. This process reveals the intrinsic “spectral fingerprints” in machine-generated texts–patterns that remain invisible in time domain. Comprehensive evaluations on three well-curated datasets (RAID, EvoBench, and Domain-Shift) show that our method achieves a new state-of-the-art. It not only achieves superior accuracy but also exhibits remarkable robustness against sophisticated attacks, generalization across out-of-distribution topics and unseen evolving LLMs. Our results validate the efficacy of spectral analysis as a promising paradigm for LLM-generated texts detection.
Imbalanced data are commonly present in real-world applications. While data synthesis can effectively mitigate data scarcity for rare classes, and LLMs have revolutionized text generation, the application of LLMs to the synthesis of relational/structured tabular data remains underexplored. Moreover, existing approaches lack an effective feedback mechanism to guide LLMs in continuously optimizing the quality of the generated data throughout the synthesis process. In this work, we propose RDDG, Relational Data generator with Dynamic Guidance, which is a unified in-context learning framework that employs progressive chain-of-thought (CoT) steps to generate tabular data for enhancing downstream imbalanced classification performance. RDDG first uses core set selection to identify representative samples from the original data, then utilizes in-context learning to discover the inherent patterns and correlations among attributes within the core set, and subsequently generates tabular data while preserving the aforementioned constraints. More importantly, it incorporates a self-reinforcing feedback mechanism that provides automatic assessments of the quality of the generated data, enabling continuous quality optimization throughout the generation process. Experimental results on multiple real and synthetic datasets demonstrate that RDDG outperforms existing approaches in both data fidelity and downstream imbalanced classification performance.
AI, Take the Wheel: What Drives Delegation and Trust in Human–Computer Cooperative Question Answering?
PDF ↗AI systems are fallible, and humans can make mistakes in deciding whether to trustAI over their own judgment. Thus, improving human-AI collaboration requires that we understand when,why, and how humans decide to rely on AI. We study two reliance decisions: delegating a task toAI without seeing its output (whether AI is used) and evaluating AI suggestions to decidewhether to adopt them how AI output shapes final decisions).Both matter for effective collaboration, yet prior work lacks naturalistic experiments capturing both patternsfor the same users. We address this gap by studying collaborative human–AI teams competing in aquestion-answering game in which humans can choose when and how to work with AI agents to win.Our 24 matches pair 23 expert humans with 16 AI agents, capturing 387 delegation and 1440 adoption decisions.While human–AI collaboration performs better than either AI or humansalone, humans make suboptimal collaboration decisions, bothunder-relying on correct AI suggestions (3.7% of opportunities missed) and over-relying when AI misleads them (1.5%).Both parties contribute wrong answers: reported model confidence is near chance when humans and AI disagree, while confirmation bias drives higher under-reliance (60.7%) when an AI suggestion agrees with humans’ initial incorrect answer.
Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by tightly coupling the drafter with the target model, the verification mechanism itself remains largely unchanged, relying on strict token-level rejection sampling. In practice, modern LLMs frequently operate in low-margin regimes where the target model exhibits weak preference among top candidates. In such cases, rejecting plausible runner-up tokens yields negligible information gain while incurring substantial rollback cost, leading to a fundamental inefficiency in verification.We propose Margin-Aware Speculative Verification, a training-free and domain-agnostic verification strategy that adapts to the target model’s local decisiveness. Our method conditions verification on decision stability measured directly from the target logits and relaxes rejection only when strict verification provides minimal benefit. Importantly, the approach modifies only the verification rule and is fully compatible with existing target-coupled speculative decoding frameworks. Extensive experiments across model scales ranging from 8B to 235B demonstrate that our method delivers consistent and significant inference speedups over state-of-the-art baselines while preserving generation quality across diverse benchmarks. The code is available at https://github.com/5SSjw/MARS.
MDocRAG-RL: Empowering Multi-Modal Document RAG via Complex Visual Reasoning with Reinforcement Learning
PDF ↗While Retrieval-Augmented Generation(RAG) enhances multi-modal large language models(MLLMs) by introducing external knowledge, existing RAG systems still face significant limitations when dealing with complex visual reasoning. On one hand, MLLMs, being generative models, produce suboptimal embeddings for retrieval tasks. On the other hand, existing methods naively insert images into context without adequate visual perception, thereby limiting reasoning capabilities. To address these challenges, we propose MDocRAG-RL, a novel RAG framework for complex visual reasoning. We design specialized pre-training and fine-tuning tasks to enable MLLMs to compress visual document representations and align textual and visual embeddings for improved retrieval efficiency. Additionally, we design a visual perception action space for the generator that allows progressive coarse-to-fine information acquisition from visually-rich documents. Furthermore, we develop a reinforcement learning framework to enhance the complex visual reasoning capability of the RAG system. Extensive experiments on multiple challenging benchmarks demonstrate the significant effectiveness of our approach, achieving state-of-the-art performance across various benchmarks.
Reward models (RMs) play a critical role in aligning large language models (LLMs) with human preferences. Yet in the domain of tool learning, the lack of RMs specifically designed for function-calling tasks has limited progress toward more capable agentic AI. We introduce ToolRM, a family of lightweight reward models tailored for general tool-use scenarios. To build these models, we propose a novel pipeline that constructs high-quality pairwise preference data using rule-based scoring and multidimensional sampling. This yields ToolPref-Pairwise-30K, a diverse, balanced, and challenging preference dataset that supports both generative and discriminative reward modeling. We also introduce TRBench_{BFCL}, a benchmark built on the agent evaluation suite BFCL to evaluate RMs on tool calling tasks. Trained on our constructed data, models from the Qwen3-4B/8B series achieve up to 17.94% higher accuracy, substantially outperforming frontier LLMs and RMs in pairwise reward judgments. Beyond training objectives, generative ToolRM generalizes to broader critique tasks, including Best-of-N sampling and self-correction. Experiments on ACEBench highlight its effectiveness and efficiency, enabling inference-time scaling while reducing output token usage by over 66%. Its support for downstream RL training further validates its practical utility. We release data to facilitate future research.
Large language models (LLMs) exhibit systematic Western-centric bias, yet whether prompting in non-Western languages (e.g., Chinese) can mitigate this remains understudied. Answering this question requires rigorous evaluation and effective mitigation, but existing approaches fall short on both fronts: evaluation methods force outputs into predefined cultural categories without a neutral option, while mitigation relies on expensive multi-cultural corpora or agent frameworks that use functional roles (e.g., Planner–Critique) lacking explicit cultural representation. To address these gaps, we introduce CEBiasBench, a Chinese–English bilingual benchmark, and Multi-Agent Vote (MAV), which enables explicit "no bias” judgments. Using this framework, we find that Chinese prompting merely shifts bias toward East Asian perspectives rather than eliminating it. To mitigate such persistent bias, we propose Multi-Agent Cultural Debate (MACD), a training-free framework that assigns agents distinct cultural personas and orchestrates deliberation via a "Seeking Common Ground while Reserving Differences” strategy. Experiments demonstrate that MACD achieves 57.6% average No Bias Rate evaluated by LLM-as-judge and 86.0% evaluated by MAV (vs. 47.6% and 69.0% baseline using GPT-4o as backbone) on CEBiasBench and generalizes to the Arabic CAMeL benchmark, confirming that explicit cultural representation in agent frameworks is essential for cross-cultural fairness.