Generative retrieval directly decode a document identifier (i.e., docid) in response to a query, making it impossible to provide users with explanations as an answer for “why is this document retrieved?”. To address this limitation, we propose Hierarchical Category Path-Enhanced Generative Retrieval (HyPE), which enhances explainability by first generating hierarchical category paths step-by-step then decoding docid. By leveraging hierarchical category paths which progress from broader to more specific semantic categories, HyPE can provide detailed explanation for its retrieval decision. For training, HyPE constructs category paths with external high-quality semantic hierarchy, leverages LLM to select appropriate candidate paths for each document, and optimizes the generative retrieval model with path-augmented dataset. During inference, HyPE utilizes path-aware ranking strategy to aggregate diverse topic information, allowing the most relevant documents to be prioritized in the final ranked list of docids. Our extensive experiments demonstrate that HyPE not only offers a high level of explainability but also improves the retrieval performance. We provide the code and a live demo of HyPE at https://augustinlib.github.io/HyPE/
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
Medical multimodal large language models are increasingly deployed in high-stakes clinical settings, yet current safety evaluations largely overlook a critical failure mode: covert semantic drift that accumulates across clinically plausible multi-turn interactions. Such drift can lead models to gradually exaggerate or conceal critical medical findings without triggering explicit safety mechanisms. We propose MSIA (Medical Semantic Infiltration Attack), a framework for modeling and inducing multi-turn medical semantic jailbreaks in clinical dialogues. MSIA enables the controlled optimization of cumulative semantic drift under stealth constraints through adaptive strategy selection and closed-loop reward feedback grounded in medical evidence. Experiments on chest X-ray–based multimodal medical dialogues show that MSIA consistently outperforms existing jailbreak methods across GPT-4o, Claude, and Gemini, achieving an average attack success rate of 76.67%. These results expose substantial and previously underestimated vulnerabilities of medical LLMs in realistic multi-turn clinical interactions. Code is available here: https://github.com/HeYamo/MSIA.
Large Reasoning Models (LRMs) allocate substantial inference-time compute to Chain-of-Thought (CoT) reasoning, improving performance on mathematics, scientific QA, and tool usage. However, this introduces overthinking: LRMs often reach a correct intermediate solution, continue reasoning, and overwrite it with an incorrect answer. We first demonstrate that oracle stopping—where we inject lt;/think gt; at every sentence boundary and select the best stopping point in hindsight—improves average accuracy by 8% while reducing thinking tokens by 72%, exposing substantial overthinking. Motivated by this finding, we propose ThinkBrake, which monitors the log-probability margin between the top continuation token and lt;/think gt; at sentence boundaries, stopping reasoning when this margin narrows. ThinkBrake requires no training and achieves favorable accuracy–efficiency trade-offs across math, scientific QA, and tool usage benchmarks, reducing thinking token usage by up to 30%. Furthermore, we provide theoretical analysis showing that ThinkBrake is equivalent to test-time realignment with a reward bonus for the lt;/think gt; token.
The dominant paradigm in video retrieval relies on embedding-based full-corpus scanning, which suffers from inherent computational inefficiency and the semantic asymmetry between information-dense videos and sparse textual queries. To bridge this gap, we introduce **MAVIS**, a novel multi-agent framework that rethinks retrieval as cooperative reasoning rather than brute-force search. MAVIS first bridges the granularity mismatch by parsing raw videos into a **Structured Semantic Library**, enabling explicit attribute-level indexing. During retrieval, a planner decomposes complex user intents into atomic sub-tasks, dispatching specialized agents to independently nominate candidates. Crucially, MAVIS employs a **Logic-aware Debate** mechanism with a strict veto protocol, where agents collaboratively prune logical mismatches to identify a compact set of "controversial” candidates for fine-grained verification. This agentic workflow effectively bypasses the inefficiency of full-library traversal. Extensive experiments on MSR-VTT, MSVD, and ActivityNet demonstrate that MAVIS achieves competitive performance without task-specific fine-tuning, offering a scalable and interpretable alternative to traditional dual-encoder approaches.
ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction
PDF ↗LLM-based universal information extraction (UIE) methods often rely on additional information beyond the original training data, which increases training complexity yet often yields limited gains. To address this, we propose ProUIE, a Macro-to-Micro progressive learning approach that improves UIE without introducing any external information. ProUIE consists of three stages: (i) macro-level Complete Modeling (CM), which learns NER, RE, and EE along their intrinsic difficulty order on the full training data to build a unified extraction foundation, (ii) meso-level Streamlined Alignment (SA), which operates on sampled data with simplified target formats, streamlining and regularizing structured outputs to make them more concise and controllable, and (iii) micro-level Deep Exploration (DE), which applies GRPO with stepwise fine-grained rewards (SFR) over structural units to guide exploration and improve performance. Experiments on 36 public datasets show that ProUIE consistently improves unified extraction, outperforming strong instruction-tuned baselines on average for NER and RE while using a smaller backbone, and it further demonstrates clear gains in production-oriented information extraction.
Sequential diagnosis requires balancing diagnostic accuracy against resource costs through iterative information gathering. Existing Large Language Model (LLM) approaches exhibit a critical knowledge-reasoning gap: despite encoding extensive medical knowledge, they struggle to reason systematically under cost constraints, often resorting to excessive testing. We propose GraphDx, a knowledge-enhanced framework with two core innovations. First, we design an automated pipeline that leverages LLMs to construct Medical Diagnosis Knowledge Graphs (MDKGs) with quantized typicality, action-centric topology, and dual-objective attributes for both diagnostic relevance and cost-sensitivity. Second, we introduce three collaborative agents (Perception, Reasoning, and Decision) where the Perception and Decision Agents handle language understanding and generation, while the Reasoning Agent performs deterministic evidence scoring and cost-aware planning on the MDKG. Experiments on MedQA and MIMIC-IV across three LLM backbones (DeepSeek-V3, Kimi-k2, Llama-3.3) show that GraphDx improves diagnostic success rates from 50–68% to 79–93% while reducing test costs by 20–54%, providing a robust, economical, and interpretable solution for automated clinical diagnosis.
Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large language models (LLMs). Existing memory frameworks provide limited support for temporally structured information across hierarchical levels, often leading to fragmented memories and unstable long-horizon personalization. We present TiMem, a temporal–hierarchical memory framework that organizes conversations through a Temporal Memory Tree (TMT), enabling systematic memory consolidation from raw conversational observations to progressively abstracted persona representations. TiMem is characterized by three core properties: (1) temporal–hierarchical organization through TMT; (2) semantic-guided consolidation that enables memory integration across hierarchical levels without fine-tuning; and (3) complexity-aware memory recall that balances precision and efficiency across queries of varying complexity. Under a consistent evaluation setup, TiMem achieves state-of-the-art accuracy on both benchmarks, reaching 75.30% on LoCoMo and 76.88% on LongMemEval-S. It outperforms all evaluated baselines while reducing the recalled memory length by 52.20% on LoCoMo. Manifold analysis indicates clear persona separation on LoCoMo and reduced dispersion on LongMemEval-S. Overall, TiMem treats temporal continuity as a first-class organizing principle for long-horizon memory in conversational agents. The code is available at https://github.com/TiMEM-AI/timem.
PROGRAM: Programmatic Retrieval Optimization with Generative Reasoning and Augmented Multi-queries
PDF ↗Current retrieval-augmented generation (RAG) methods struggle with complex multi-hop reasoning, relying on unstructured semantic matching that lacks the logical structure needed to systematically guide retrieval. We introduce Programmatic Retrieval Optimization with Generative Reasoning and Augmented Multi-queries (PROGRAM), a novel framework that elevates retrieval to structured, program-guided reasoning. PROGRAM treats retrieval as execution of specific program types, such as logical, temporal, causal, and so forth, through three stages of ’Program-Type Selection’ with dual-metric optimization, ’Iterative Active Program Pruning’ with evidence accumulation, and ’Final Answer Generation’ with reranking. Evaluated on five benchmarks including HotPotQA, 2WikiMultihopQA, ARC-Challenge, MMLU-Pro, and MedQA with various LLMs, PROGRAM achieves state-of-the-art performance with up to 24% relative improvement on HotPotQA and 13.2% on MedQA over strong baselines including FLARE, ProbTree and Self-RAG.
Safety-critical traffic reasoning requires contrastive consistency: models must detect true hazards when an accident occurs, and reliably reject plausible-but-false hypotheses under near-identical counterfactual scenes. We present CCTVBench, a Contrastive Consistency Traffic VideoQA Benchmark built on paired real accident videos and world-model-generated counterfactual counterparts, together with minimally different, mutually exclusive hypothesis questions. CCTVBench enforces a single structured decision pattern over each video question quadruple and provides actionable diagnostics that decompose failures into positive omission, positive swap, negative hallucination, and mutual-exclusivity violation, while separating video versus question consistency. Experiments across open-source and proprietary video LLMs reveal a large and persistent gap between standard per-instance QA metrics and quadruple-level contrastive consistency, with unreliable none-of-the-above rejection as a key bottleneck. Finally, we introduce C-TCD, which leverages the semantically exclusive counterpart video as the contrast input at inference time, improving both instance-level QA and contrastive consistency.
Personality detection aims to label an individual’s traits via identifying linguistic cues from his or her written text. Previous approaches typically perform a direct mapping between text and trait labels or apply static reasoning to this task.In this paper, we argue that dynamic reasoning, underpinned by psychological theory, is essential for personality trait inference. To address this, we propose PsyPath, a novel framework that models personality detection as a process of psychologically-guided self-exploration. By enabling large language models (LLMs) to dynamically generate and answer psychologically meaningful questions, our method creates a dynamic reasoning path to explore the underlying dimensions of personality traits. This mechanism not only makes the reasoning process transparent, but also helps the model understand personality nuances in a way that mirrors expert psychological reasoning.For the "guided self-exploration", we propose a novel hybrid scoring mechanism to step-by-step evaluate the generated nodes in the reasoning paths that balances psychological coherence (black-box scoring) and model output dynamics (white-box scoring). This reasoning-based formulation inherently reflects how psychologists assess personality, as they rely on iterative, diagnostic reasoning. Experiments on two benchmark datasets demonstrate that PsyPath consistently outperforms strong baselines, yielding improvements in predictive accuracy and model interpretability.Moreover, the generated reasoning paths provide psychologically meaningful training data, significantly improving performance and psychologically grounded interpretability in downstream tasks.
Personalized glucose regulation remains a central yet unresolved challenge in precision nutrition, as postprandial glucose response varies substantially across individuals. Existing approaches based on glycemic indices fail to adequately account for such heterogeneity and lack the mechanism to dynamically adjust meals based on personal physiological feedback. In this context, recent advances in LLM-based agents offer a promising direction, as they enable context-aware reasoning and iterative refinement. Inspired by this, we propose a physio-feedback agentic loop, a unified system that integrates individualized absorption modeling with dietary intervention to regulate glucose response. Specifically, we develop a Physiology-Aware Glucose Predictor to model individualized absorption dynamics through a learnable Temporal Physiological Absorption Decay Module. We then construct a Prediction-Driven Two-Stage Meal Optimization Agent that iteratively refines real-world meals using predicted outcomes as explicit feedback. Through extensive experiments on multiple public datasets, we demonstrate that our method not only improves prediction accuracy but also effectively reduces glucose excursions. To the best of our knowledge, this paper marks the first step in integrating physiological learning with an LLM-based agent for personalized glucose regulation.
Understanding and controlling the behavior of large language models (LLMs) is an increasingly important topic in multilingual NLP. Beyond prompting or fine-tuning, \textit{language steering}, i.e., manipulating internal representations during inference, has emerged as a more efficient and interpretable technique for adapting models to a target language. Yet, no dedicated benchmarks or evaluation protocols exist to quantify the effectiveness of steering techniques. We introduce CLaS-Bench, a lightweight parallel-question benchmark for evaluating language-forcing behavior in LLMs across 32 languages, enabling systematic evaluation of multilingual steering methods. We evaluate a broad array of steering techniques, including residual-stream DiffMean interventions, probe-derived directions, language-specific neurons, PCA/LDA vectors, Sparse Autoencoders, and prompting baselines. Steering performance is measured along two axes: language control and semantic relevance, combined into a single harmonic-mean steering score. We find that across languages simple residual-based DiffMean method consistently outperforms all other methods. Moreover, a layer-wise analysis reveals that language-specific structure emerges predominantly in later layers and steering directions cluster based on language family. CLaS-Bench is the first standardized benchmark for multilingual steering, enabling both rigorous scientific analysis of language representations and practical evaluation of steering as a low-cost adaptation alternative.
Self-Consistency improves reasoning reliability through multi-sample aggregation, but incurs substantial inference cost. Adaptive self-consistency methods mitigate this issue by adjusting the sampling budget; however, they rely on count-based stopping rules that treat all responses equally, often leading to unnecessary sampling. We propose Reliability-Aware Adaptive Self-Consistency (ReASC), which addresses this limitation by reframing adaptive sampling from response counting to evidence sufficiency, leveraging response-level confidence for principled information aggregation. ReASC operates in two stages: a single-sample decision stage that resolves instances confidently answerable from a single response, and a reliability-aware accumulation stage that aggregates responses by jointly leveraging their frequency and confidence. Across five models and four datasets, ReASC consistently achieves the best accuracy-cost trade-off compared to existing baselines, yielding improved inference efficiency across model scales from 3B to 27B parameters. As a concrete example, ReASC reduces inference cost by up to 70% relative to self-consistency while preserving accuracy on GSM8K using Gemma-3-4B-it.
Large Language Models (LLMs) as judges across various scenarios such as assessing model responses is becoming an increasingly accepted paradigm. However, existing judgment approaches often rely on trained judgers using fixed preference data, which tend to overlook diverse user preferences and struggle to adapt to real-world human-AI dialogue scenarios. To address these limitations, we propose SenseJudge, a customizable judgment framework driven by human preferences and SenseBench, a diverse and challenging instruction following benchmark derived from real-world multi-turn interactions. We applied the automatic judgment framework and benchmark to two tasks: 1) LLMs as personalized judges, and 2) model ranking. We conducted extensive experiments, and the results demonstrate that the SenseJudge framework surpasses other judgment methods and models in the LLMs-as-personalized-judges task and achieves model ranking that aligns with real human sense. Additionally, we conducted analyses on position bias and consistency, alongside ablation studies, which affirmed the robustness of SenseJudge.
The rapid spread of fake news threatens social stability and public trust, highlighting the urgent need for its effective detection.Although large language models (LLMs) show potential in fake news detection, they are limited by knowledge cutoff and easily generate factual hallucinations when handling time-sensitive news.Furthermore, the thinking of a single LLM easily falls into early stance locking and confirmation bias, making it hard to handle both content reasoning and fact checking simultaneously.To address these challenges, we propose ZoFia, a two-stage zero-shot fake news detection framework.In the first retrieval stage, we propose novel Hierarchical Salience and Salience-Calibrated Minimum Marginal Relevance (SC-MMR) algorithm to extract core entities accurately, which drive dual-source retrieval to overcome knowledge and evidence gaps.In the subsequent stage, a multi-agent system conducts multi-perspective reasoning and verification in parallel and achieves an explainable and robust result via adversarial debate.Comprehensive experiments on two public datasets show that ZoFia outperforms existing zero-shot baselines and even most few-shot methods.Our code has been open-sourced to facilitate the research community at https://github.com/SakiRinn/ZoFia.
Large language models (LLMs) increasingly act as tool-using agents, and existing methods for evaluating and optimizing tool usage by LLMs typically assume a static tool environment with fixed APIs and documentation. In practice, toolsets evolve as tools are added, changed, or deprecated, introducing instability for agents that must retain prior competence while adapting to new capabilities. We formalize this challenge as the stability–adaptation dilemma. To address it, we propose ContDa, a continual documentation adaptation framework that provides a generalizable solution to this problem, enabling LLM agents to self-evolve by updating tool documentation. ContDa combines relation-guided exploration, which leverages functionally related existing tools as anchors to probe and identify new tool capabilities, with relation-aware adjustment that organizes overlapping tools and explicitly encodes usage preferences and fallback options among them. We then introduce complementary metrics that disentangle performance from stability and adaptation. Experiments across three evolution patterns on dynamic extensions of StableToolBench and RestBench show that ContDa consistently improves average performance by enhancing the discovery of new capabilities while incurring only limited loss of previously solved tasks, demonstrating documentation adaptation as an effective and lightweight mechanism for robust tool use in evolving environments. Our code is available at https://github.com/Bingo-W/ContDa.
D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
PDF ↗Supervised Fine-Tuning (SFT) accelerates task-specific large language models (LLMs) development, but the resulting proliferation of fine-tuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single pre-trained LLM with multiple compressed delta weights. However, existing methods fail on models fine-tuned with large-scale datasets. We find that larger SFT data scale amplifies delta parameter magnitude, singular values, and entropy, exacerbating compression errors. To tackle this, we propose D-QRELO ( \textbf{D}elta Compression via \textbf{Q}uantization and \textbf{R}sidual \textbf{Lo}w-Rank), a novel training- and data-free delta compression method. It combines coarse-grained one-bit quantization to capture the dominant structure of the delta, followed by compensated residual low-rank approximation to recover fine-grained details from the smaller residual error. Experiments on various LLMs spanning dense and MoE architectures across multiple domains under this challenging setting demonstrate that D-QRELO outperforms existing methods. Moreover, we establish key design principles for delta compression through extensive empirical analysis, demonstrating how task difficulty, architecture, and layer positioning create predictable patterns that can guide optimal compression strategies in production systems.
Student Personas (SPs) are emerging as infrastructure for educational LLMs, yet prior work often relies on ad-hoc prompting or hand-crafted profiles with limited control over educational theory and population distributions. We formalize this as Theory-Aligned and Distribution-Controllable Persona Generation (TAD-PG) and introduce HACHIMI, a multi-agent Propose-Validate-Revise framework that generates theory-aligned, quota-controlled personas. HACHIMI factorizes each persona into a theory-anchored educational schema, enforces developmental and psychological constraints via a neuro-symbolic validator, and combines stratified sampling with semantic deduplication to reduce mode collapse. The resulting HACHIMI-1M corpus comprises 1 million personas for Grades 1-12. Intrinsic evaluation shows near-perfect schema validity, accurate quotas, and substantial diversity, while external evaluation instantiates personas as student agents answering CEPS and PISA 2022 surveys; across 16 cohorts, math and curiosity/growth constructs align strongly between humans and agents, whereas classroom-climate and well-being constructs are only moderately aligned, revealing a fidelity gradient. All personas are generated with Qwen2.5-72B, and HACHIMI provides a standardized synthetic student population for group-level benchmarking and social-science simulations. Resources available at https://github.com/ZeroLoss-Lab/HACHIMI.
FAQ: Mitigating Quantization Error via Regenerating Calibration Data with Family-Aware Quantization
PDF ↗Although post-training quantization (PTQ) provides an efficient numerical compression scheme for deploying large language models (LLMs) on resource-constrained devices, the representativeness and universality of calibration data remain a core bottleneck in determining the accuracy of quantization parameters. Traditional PTQ methods typically rely on limited samples, making it difficult to capture the activation distribution during the inference phase, leading to biases in quantization parameters. To address this, we propose **FAQ** (Family-Aware Quantization), a calibration data regeneration framework that leverages prior knowledge from LLMs of the same family to generate high-fidelity calibration samples. Specifically, FAQ first inputs the original calibration samples into a larger LLM from the same family as the target model, regenerating a series of high-fidelity calibration data using a highly consistent knowledge system. Subsequently, this data, carrying Chain-of-Thought reasoning and conforming to the expected activation distribution, undergoes group competition under expert guidance to select the best samples, which are then re-normalized to enhance the effectiveness of standard PTQ. Experiments on multiple model series, including Qwen3-8B, show that FAQ reduces accuracy loss by up to 28.5% compared to the baseline with original calibration data, demonstrating its powerful potential and contribution.
CoTrust: Privacy-Preserving Collaboration Between Large and Small Language Models in Trusted Execution Environments
PDF ↗Services powered by large language models (LLMs) provide powerful text generation capabilities, but accessing sensitive user inputs raises serious privacy concerns. Trusted Execution Environments (TEEs) provide a secure computation environment, enabling sensitive inputs to be safely processed. However, directly deploying high-capacity LLMs in TEEs is often prohibitively expensive due to computation and memory constraints. To reconcile privacy, efficiency, and generation quality, we propose CoTrust, a privacy-preserving collaborative inference framework that combines LLMs with small language models (SLMs) inside TEE. CoTrust uses multiple de-identified views to let the LLM produce a consensus scaffold capturing answer reasoning without exposing private information, which the SLM then grounds in the full input to generate the final response. Experiments on multiple question answering and summarization benchmarks show that CoTrust approaches the performance of unconstrained LLMs, outperforms existing privacy-preserving baselines, and maintains strong privacy protection, while remaining efficient in a TDX-based TEE implementation.