Multi-party dialogue discourse parsing aims to identify dependency structures and relation types between utterances in conversations. Previous studies are mostly limited to textual modality or two-party dialogue, failing to meet the multimodal and multi-party settings. In this paper, we construct the first publicly available English multimodal dataset DraDDP for multi-party dialogue discourse parsing, based on American TV dramas. DraDDP contains 495 dialogue segments with 6,374 utterances and 9.1 hours of parallel video content, covering rich multi-party interaction scenarios. Moreover, we establish comprehensive benchmarks by evaluating this task on DraDDP and conducting in-depth analysis on the impact of different modalities. Experimental results demonstrate the value of multimodal information in capturing dialogue structures and relation types. We will publicly release the dataset, annotation guidelines, and code to promote future research in multimodal dialogue understanding.
论文检索
输入标题、作者或关键词，从 9,460 篇学术成果中精准定位
The transition to end-to-end Multimodal Large Language Models (MLLMs) has positioned these architectures as active social evaluators in high-stakes domains. However, it remains unclear whether these models maintain objective auditory perception or succumb to the "Hearing with Eyes" phenomenon, where visual racial cues distort linguistic proficiency evaluations. We investigate this cross-modal bias by constructing a controlled counterfactual dataset utilizing a Visual Matched-Guise Paradigm. By pairing identical native audio with diverse visual personas across English and Korean contexts, we reveal a distinct Cultural Asymmetry in model behavior. In Anglophone settings, most closed models exhibit Reverse Linguistic Stereotyping, hallucinating non-native accents for Asian speakers despite standard native audio. Conversely, in Korean settings, the same models assign baseline-relative competence premiums across all visual personas, with the largest gains for out-group (White/Black) speakers, consistent with Expectancy Violation Theory. Our findings demonstrate that MLLMs do not merely process sensory inputs but actively reproduce context-dependent sociolinguistic ideologies.
We introduce a constraint-selection-based experiment design for measuring narrative preferences of Large Language Models (LLMs). This design offers an interpretable lens on LLMs’ narrative selection behavior. We developed a library of 200 narratology-grounded constraints and prompted selections from six LLMs under three different instruction types: basic, quality-focused, and creativity-focused. Findings demonstrate that models consistently prioritize Style over narrative content elements like Event, Character, and Setting. Style preferences remain stable across models and instruction types, whereas content elements show cross-model divergence and instructional sensitivity. These results suggest that LLMs have latent narrative preferences, which should inform how the NLP community evaluates and deploys models in creative domains.
Dynamic Graph Navigation via Triplet Chains for Structure-Aware Retrieval-Augmented Generation
PDF ↗Retrieval-Augmented Generation (RAG) was proposed to address the hallucination question of large language models (LLMs). However, the traditional RAG framework has certain limitations: for simple questions, the search results often introduce a large amount of irrelevant information; while for complex questions, the lengthy reference knowledge provided by the retrieval lacks structural information. Therefore, we proposed a structure-aware RAG, which achieves noise removal in retrieval through multi-chain graph navigation reasoning(Trig-Nav). This method constructs question triple reasoning chains and reference knowledge graphs with text attributes, allowing the system to retrieve three types of knowledge along different paths based on the requirements of LLM. It provides LLM with multi-angle and structured information input and significantly reduces noise. We conducted a comprehensive evaluation of Trig-Nav, comparing it with baseline methods across multiple datasets.Compared to traditional RAG, there is an average improvement of 6% in effectiveness. The results showed that Trig-Nav significantly enhances the model’s performance, validating the effectiveness of this approach.
Research in cross-lingual modeling for historical and extremely low-resource languages is hindered by the absence of standardized evaluation benchmarks. To address this, we present ManCC—the first task-anchored benchmark for Manchu–Classical Chinese translation. ManCC consists of a high-quality parallel corpus of 16,627 sentence pairs, derived from the Qing-dynasty historical text Manwen Laodang-Taizong, and a reproducible evaluation protocol that combines automatic metrics (BLEU and chrF) with a three-dimensional human assessment (fidelity, fluency, linguistic normativity). Through systematic evaluation across three model families (non-pretrained, multilingual pretrained, and large language models), we find that linguistic differences significantly influence performance, broader language coverage in multilingual pretraining facilitates low-resource transfer, and automatic metrics often fail to capture essential errors in historical translation—underscoring the necessity of human evaluation. ManCC not only provides foundational resources for Manchu–Classical Chinese translation but also establishes a diagnosable, reproducible platform for cross-lingual modeling of historical low-resource languages.
Large Language Models (LLMs) used in Retrieval-Augmented Generation (RAG) can amplify demographic bias: retrievers may surface skewed context and generators can propagate that skew into decisions. Prior work typically treats fairness in retrieval or generation in isolation, leaving end-to-end fairness in RAG underexplored. We propose a post-hoc pipeline that jointly controls both stages: (i) a Fair Greedy Reranker (FGR) that builds prefix-balanced slates toward a target group mix; (ii) a Residual Slate Bias Estimator (RSBE) using signed, prefix-sensitive NDKL to quantify remaining skew; and (iii) Confidence-Gated Logit Calibration (CGLC) that converts the residual signal into small and margin-focused logit corrections without retraining. On an occupation classification task, our approach reduces retriever-side skew (lowest NDKL among baselines for both dense and sparse retrievers) and achieves the lowest generator-side disparity (e.g., Risk Difference) while largely preserving utility. The same calibration can be tuned to alternative fairness criteria (e.g., Equal Opportunity) with minimal utility loss.
Safety Guardrails of Large Language Models Are Vulnerable to Value-Driven Adversarial Prompting
PDF ↗In the real world, the execution of a task often depends on the executor’s recognition of its value. Motivated by this observation, we propose the value-driven jailbreak attack (VDJA), a simple and effective black-box jailbreak method against large language models (LLMs). VDJA first exploits the phenomenon that LLMs tend to agree with humans to induce LLMs to affirm the moral value of harmful tasks. During autoregressive generation, these value-endorsement tokens function as an implicit value prior, making LLMs more likely to accept and generate harmful content. Extensive experiments on five state-of-the-art (SOTA) LLMs demonstrate the superiority of VDJA. Using only a single query and without concealing harmful instructions, VDJA achieves an average attack success rate (ASR) of 91.8% on JailbreakBench and 95.2% on the AdvBench subset, showcasing SOTA jailbreak success rates and attack efficiency. Most importantly, our work suggests a previously underexplored vulnerability in the safety guardrails of LLMs, which highlights the urgent need to enhance their robustness.
Multilingual retrieval-augmented generation (mRAG) is often implemented within a fixed retrieval space, typically via query or document translation or multilingual embedding vector representations. However, this approach may be inadequate for culturally grounded queries, in which retrieval-condition misalignment may occur. Even strong retrievers and generators may struggle to produce culturally relevant answers when sourcing evidence from inappropriate linguistic or regional contexts. To this end, we introduce CORAL (COntext-aware Retrieval with Agentic Loop, an adaptive retrieval methodology for mRAG that enables iterative refinement of both the retrieval space (corpora) and the retrieval probe (query) based on the quality of the evidence. The overall process includes: (1) selecting corpora, (2) retrieving documents, (3) critiquing evidence for relevance and cultural alignment, and (4) checking sufficiency. If the retrieved documents are insufficient to answer the query correctly, the system (5) reselects corpora and rewrites the query. Across two cultural QA benchmarks, CORAL achieves up to a 3.58%p accuracy improvement on low-resource languages relative to the strongest baselines.
Large language models (LLMs) are commonly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT) or in-context learning (ICL). Recently, ICL-driven embedding-based adaptation has been proposed as a distinct task adaptation paradigm. It derives task-specific embeddings from intermediate activations using few-shot prompts and injects them during inference. Despite its conceptual appeal, this approach has not demonstrated consistent performance gains over PEFT or ICL, and its empirical advantages have been limited in practice. We propose Soft head-selection for ICL-derived Task Embeddings (SITE), a gradient-based method that identifies task-relevant attention heads to enable effective task embedding injection. Across various types of open-ended generation, reasoning, and natural language understanding tasks, SITE significantly outperforms prior embedding-based adaptation methods and few-shot ICL, while using substantially fewer trainable parameters than PEFT. Experiments on 12 LLMs ranging from 4B to 70B parameters demonstrate the generality of our approach, and intra-task and inter-task activation patching analyses further provide new mechanistic insights by revealing strong task dependence in attention head functionality.
Large language models (LLMs) suffer significant performance degradation when user instructions and context are distributed over multiple conversational turns, yet multi-turn (MT) interactions dominate chat interfaces. The routine approach of appending full chat history to prompts rapidly exhausts context windows, leading to increased latency, higher computational costs, and diminishing returns as conversations extend. We introduce **MT-OSC**, a **O**ne-off **S**equential **C**ondensation framework that efficiently and automatically condenses chat history in the background without disrupting the user experience. MT-OSC employs a Condenser Agent that uses a few-shot inference-based Condenser and a lightweight Decider to selectively retain essential information, reducing token counts by up to 72% in 10-turn dialogues. Evaluated across 13 state-of-the-art LLMs and diverse multi-turn benchmarks, MT-OSC consistently narrows the multi-turn performance gap—yielding improved or preserved accuracy across datasets while remaining robust to distractors and irrelevant turns. Our results establish MT-OSC as a scalable solution for multi-turn chats, enabling richer context within constrained input spaces, reducing latency and operational cost, while balancing performance.
Multilingual Retrieval-Augmented Generation (mRAG) systems often exhibit a perceived preference for high-resource languages, particularly English, resulting in the widespread adoption of English pivoting. While prior studies attribute this advantage to the superior English-centric capabilities of Large Language Models (LLMs), we find that such measurements are significantly distorted by structural priors inherent in evaluation benchmarks. Specifically, we identify exposure bias and a gold availability prior—both driven by the disproportionate concentration of resources in English—as well as cultural priors rooted in topic locality, as factors that hinder accurate assessment of genuine language preference. To address these biases, we propose DeLP (Debiased Language Preference), a calibrated metric designed to explicitly factor out these structural confounds. Our analysis using DeLP reveals that the previously reported English preference is largely a byproduct of evidence distribution rather than an inherent model bias. Instead, we find that retrievers fundamentally favor monolingual alignment between the query and the document language. Building on this insight, we introduce DELTA (DEbiased Language preference–guided Text Augmentation), a lightweight and efficient mRAG framework that strategically leverages monolingual alignment to optimize cross-lingual retrieval and generation. Experimental results demonstrate that DELTA consistently outperforms English pivoting and mRAG baselines across diverse languages.
Real-world multi-hop QA is naturally linked with ambiguity, where a single query can trigger multiple reasoning paths that require independent resolution. Since ambiguity can occur at any stage, models must navigate layered uncertainty throughout the entire reasoning chain. Despite its prevalence in real-world user queries, previous benchmarks have primarily focused on single-hop ambiguity, leaving the complex interaction between multi-step inference and layered ambiguity underexplored. In this paper, we introduce MARCH, a benchmark for their intersection, with 2,209 multi-hop ambiguous questions curated via multi-LLM verification and validated by human annotation with strong agreement. Our experiments reveal that even state-of-the-art models struggle with MARCH, confirming that combining ambiguity resolution with multi-step reasoning is a significant challenge. To address this, we propose CLARION, a two-stage agentic framework that explicitly decouples ambiguity planning from evidence-driven reasoning, significantly outperforms existing approaches, and paves the way for robust reasoning systems.
LLM-as-a-Judge, which uses LLMs to evaluate responses to open-ended questions, has seen significant growth in recent years. It has been adopted as a scalable alternative to manual human evaluation, such as crowdsourcing, which is often time-consuming and costly. However, the discrepancy between LLM-generated evaluations and human evaluations remains a critical problem in this field. To bridge this gap, we propose Multi-Aspect Panels of LLM Evaluators (MAPLE), a framework that orchestrates evaluations across multiple criteria using multiple LLMs. MAPLE integrates criterion-wise pairwise evaluations from multiple LLMs by estimating the importance of criteria and the reliability of individual evaluators. We conduct experiments with both open-source and closed-source models. Our results demonstrate that MAPLE achieves superior alignment with human evaluations compared to baselines, highlighting the importance of employing multi-agent and multi-criteria evaluation strategies.
Tiny Recursive Models (TRMs) perform iterative reasoning with an Adaptive Computation Time (ACT)-style loop, but their supervised training targets can be brittle, and their halting behavior can be difficult to tune. We introduce TRM-Planner, a two-stage teacher-cache distillation recipe that shifts compute to an offline teacher-cache stage. A frozen TRM checkpoint is unrolled for multiple refinement steps and stochastic rollouts; for each instance, we cache a small set of teacher entries (tokens, logits, step index, and quality metadata). A student TRM is then trained with the standard TRM objective plus a distillation loss computed from cached entries. Across Sudoku-Extreme and ARC-AGI-1/2, TRM-Planner shows an improvement over our reproduced TRM baseline while leaving student-time inference unchanged. On ARC1/ARC2 with 7M parameters, the two-attempt accuracy (pass@2) increases from 43.1% to 48.1% and 6.7% to 9.2%, respectively.
Large language models (LLMs) show strong reasoning and decision-making ability, but their high inference cost motivates transferring agentic skills to small language models (SLMs). Agent distillation trains SLMs on full reason–act–observe trajectories from a tool-using teacher, enabling SLMs to acquire the tool-use capabilities of large teacher models. However, some teacher-agent trajectories are simply hard for the student to learn, and their compatibility with the student can vary widely; moreover, a uniform token-level loss prevents SLMs from learning the tool-use patterns and final decisions that truly drive successful reasoning. Therefore, we propose SmartAD, a capacity-aligned agent distillation framework that improves both the distilled data and the supervision signal. SmartAD (i) selects, for each training example, the trajectory with the minimum negative log-likelihood among multiple correct teacher samples to obtain student-friendly training data, and (ii) applies a segment-weighted loss that emphasizes action execution and final decision spans over intermediate reasoning. Experiments on multi-hop QA and math benchmarks with 1.5B and 3B models show that SmartAD consistently outperforms all baselines. Overall, our method enables small models to learn the teacher’s capabilities more easily and efficiently through trajectory selection and segment-weighted supervision, achieving capacity-aligned distillation.
The Adaptive Interrogator: Detecting Trojan LLMs in Multi-Agent Systems via Evolved Conversational Strategies
PDF ↗While Large Language Model (LLM) safety has focused on single-agent, white-box settings, the adoption of Multi-Agent Systems (MAS) creates a critical blind spot: \textit{supply chain vulnerabilities in MAS ecosystems}. These systems often rely on third-party agents accessed via black-box APIs, creating risks where attackers can embed hidden triggers to manipulate collective reasoning or outputs. Because internal weights are inaccessible, traditional white-box defenses fail to detect these threats. Consequently, a critical gap exists in auditing these systems for ”Trojan” agents, \textit{i.e.}, malicious models that behave normally until triggered by specific, often multi-turn, conversational contexts. To bridge this gap, we introduce the \textbf{C}onversational \textbf{T}rojan \textbf{U}nmasking \textbf{S}ystem (\textbf{CTUS}), a black-box auditing framework that leverages an Evolutionary Algorithm (EA) to autonomously expose hidden threats. Drawing on social deduction mechanics, CTUS deploys a ”Judge” agent to evolve conversational probes that provoke Trojan agents into revealing their malicious nature without alerting benign peers. We validate CTUS across diverse architectures (Llama-2/3, Gemma, Mistral) and attack vectors (word, syntax, semantic, RLHF). Our results demonstrate that CTUS achieves superior detection rates (up to 100% in specific configurations). Furthermore, we conduct rigorous analyses to confirm the framework’s robustness, exhibiting negligible false positives on benign systems and stability across system configurations, establishing CTUS as a scalable safeguard for the multi-agent landscape.
Embedding-as-a-Service (EaaS) has emerged as a critical paradigm for commercializing large language models (LLMs). However, existing backdoor watermarking techniques are fundamentally limited to "zero-bit" detection, which prevents user-level traceability in multi-user EaaS scenarios. To address these limitations, we propose RShield, a multi-bit backdoor watermarking that enables reliable user-level attribution of LLMs for EaaS under model extraction attacks. RShield integrates Reed-Solomon error-correcting codes with orthogonal feature mapping to introduce highly-structured redundancy, constructing fault-tolerant symbol sequences for multi-bit watermark space, thereby staying recoverable even after aggressive extraction noise condition.To mitigate semantic distortion under the interference of noise channel, RShield employs a lightweight Adapter to adaptively inject multi-bit watermarks in the feature space, preserving the quality of EaaS while achieving a user-level traceability.Extensive experiments on four NLP benchmarks demonstrate that RShield efficiently achieves 100% multi-bit watermark recovery and high semantic fidelity under model extraction attacks compared to existing methods, while significantly reducing the degradation of watermarking on downstream task performance.
Large language models have been extensively studied for emotion recognition and moral reasoning as distinct capabilities, yet the extent to which emotions influence moral judgment remains underexplored. In this work, we develop an emotion-induction pipeline that infuses emotion into moral situations and evaluate shifts in moral acceptability across multiple datasets and LLMs.We observe a directional pattern: positive emotions increase moral acceptability and negative emotions decrease it, with effects strong enough to reverse binary moral judgments in up to 20% of cases, and with susceptibility scaling inversely with model capability.Our analysis further reveals that specific emotions can sometimes behave contrary to what their valence would predict (e.g., remorse paradoxically increases acceptability). A complementary human annotation study shows humans do not exhibit these systematic shifts, indicating an alignment gap in current LLMs.
Translating natural language into SQL (Text2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language models (LLMs) have significantly improved fluency in SQL generation, producing correct and executable SQL, particularly for complex queries, remains a bottleneck. We present Arctic-Text2SQL-R1, a reinforcement learning (RL) framework and model family designed to generate accurate, executable SQL using a lightweight reward signal based solely on execution correctness. Our approach avoids brittle intermediate supervision and complex reward shaping, promoting stable training and alignment with the end task. Combined with carefully curated data, strong supervised initialization, and effective training practices, Arctic-Text2SQL-R1 achieves state-of-the-art execution accuracy across six diverse Text2SQL benchmarks and ranks among the leading entries on the BIRD leaderboard. Notably, our 7B model outperforms prior 70B-class systems, highlighting the framework’s scalability and efficiency. We further demonstrate inference-time robustness through simple extensions like value retrieval and majority voting. Extensive experiments and ablation studies offer both positive and negative insights, providing practical guidance for future Text2SQL research.
On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibration
PDF ↗Diffusion Large Language Models (DLLMs) have recently achieved strong performance, e.g., masked diffusion models (MDMs) can surpass autoregressive models (ARMs) in various tasks. However, DLLMs often struggle with inaccurate early-stage predictions due to limited context, which hinders both the model’s inference efficiency and the output’s overall quality. We propose Calibrated On-Policy Self-Distillation (COPSD) for DLLMs, a simple and efficient method to calibrate early token predictions without requiring demonstration data. COPSD distills an unnormalized target distribution derived from later decoding steps into the original model, enabling more accurate early predictions during inference. Experiments on math, planning, and RLHF tasks show that COPSD improves both effectiveness and efficiency, and further enhances performance when combined with supervised fine-tuning.