Large language models have significantly advanced Multilingual Machine Translation (MMT), yet scaling to many languages while keeping quality robust across directions remains challenging.In this paper, we identify a failure mode of multilingual supervised fine-tuning (SFT) on multi-way parallel data: when such data are reused symmetrically around a pivot language (e.g., English), performance on reverse directions (X \to pivot) can drop substantially.We term this phenomenon Directional Degeneration and attribute it to excessive many-to-one mappings, which encourage shortcut learning.We propose Strategic Downsampling (SD), a simple yet effective method to mitigate this degeneration.In addition, we introduce Parallel Multilingual Prompting (PMP), which augments translation instructions with an auxiliary parallel sentence to promote cross-lingual transfer during training and enables optional test-time enhancement when auxiliary translations are available. We further develop NiuTrans.LMT (Large-scale Multilingual Translation, abbreviated as LMT), a Chinese–English-centric suite of multilingual translation models spanning four sizes (0.6B/1.7B/4B/8B) and covering 60 languages and 234 directions.Comprehensive evaluations show that LMT is competitive among open-source MMT systems, and that our 4B LMT model performs on par with or better than substantially larger baselines. We release our models and project resources to support inclusive and scalable MMT.
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
Conventional Vision-and-Language Navigation (VLN) benchmarks assume instructions are feasible and the referenced target exists, leaving agents ill-equipped to handle false-premise goals. We introduce VLN-NF, a benchmark with false-premise instructions where the target is absent from the specified area and agents must navigate, gather evidence through in-room exploration, and explicitly output NOT-FOUND. VLN-NF is constructed via a scalable pipeline that rewrites VLN instructions using an LLM and verifies target absence with a VLM, producing plausible yet factually incorrect goals. We further propose REV-SPL to jointly evaluate room reaching, exploration coverage, and decision correctness. To address this challenge, we present ROAM, a two-stage hybrid that combines supervised room-level navigation with LLM/VLM-driven in-room exploration guided by a free-space clearance prior. ROAM achieves the best REV-SPL among compared methods, while baselines often under-explore and terminate prematurely under unreliable instructions. Code and data will be released upon acceptance.
Incorporating external knowledge is crucial for knowledge-intensive tasks, such as question answering and fact checking. However, language models (LMs) may ignore relevant information that contradicts outdated parametric memory or be distracted by irrelevant contexts. While many context utilisation manipulation techniques (CMTs) have recently been proposed to alleviate these issues, few have seen systematic comparison. In this paper, we develop CUB (Context Utilisation Benchmark) - the first comprehensive benchmark designed to help diagnose CMTs under diverse noisy context conditions within retrieval-augmented generation (RAG). With this benchmark, we conduct the most extensive evaluation to date of seven state-of-the-art methods, representative of the main categories of CMTs, across three diverse datasets and tasks, applied to 11 LMs. Our findings expose critical gaps in current CMT evaluation practices, demonstrating the need for holistic testing. We reveal that most existing CMTs struggle to handle the full spectrum of context types encountered in real-world RAG scenarios. We also find that many CMTs display inflated performance on simple synthesised datasets, compared to more realistic datasets with naturally occurring samples.
Long-term conversational memory is a core capability for LLM-baseddialogue systems, yet existing benchmarks and evaluation protocolsprimarily focus on surface-level factual recall.In realistic interactions, appropriate responses often depend onimplicit constraints such as user state, goals, or values that are notexplicitly queried later.To evaluate this setting, we introduce LoCoMo-Plus, a benchmarkfor assessing cognitive memory under cue–trigger semantic disconnect,where models must retain and apply latent constraints across longconversational contexts.We further show that conventional string-matching metrics and explicittask-type prompting are misaligned with such scenarios, and propose aunified evaluation framework based on constraint consistency.Experiments across diverse backbone models, retrieval-based methods, andmemory systems demonstrate that cognitive memory remains challenging andreveals failures not captured by existing benchmarks.Our code and evaluation framework are publicly available at https://github.com/xjtuleeyf/Locomo-Plus.
Agent Newsroom: Efficient Chronological Report Generation via Dynamic Multi-Agent Collaboration
PDF ↗Many real-world applications require generating a chronological report from an evolving document stream; Timeline Summarization (TLS) provides a standard testbed for this setting. While large language models (LLMs) improve event synthesis, most LLM-based TLS systems remain monolithic: they repeatedly process overlapping evidence and often mirror the corpus’ bursty reporting patterns, producing redundant timelines with temporal/topical imbalance and high cost. We propose **MAS-TLS**, a multi-agent framework that casts TLS as a *newsroom-like* collaboration. A master editor steers balanced coverage by allocating system-visible evidence with a coverage–diversity objective; specialist reporter agents independently draft time-anchored, evidence-grounded events while cross-reviewing to limit redundancy; an adjudication round reconciles competing drafts and consolidates duplicates into a global timeline; and a non-stationary Bayesian controller adaptively staffs agents under token/time budgets. Experiments on three benchmarks show that MAS-TLS improves semantic coverage and temporal grounding while substantially reducing token usage and latency.
Know Your Place: Diagnosing Implicit Social Adaptation Failures in Chinese Large Language Models
PDF ↗As large language models (LLMs) are increasingly deployed in dialogue systems and interactive agents, their social adaptation during natural interaction has drawn growing attention. While prior work shows strong social regulation under explicit role or style instructions, it remains unclear whether LLMs can spontaneously perceive and respond to implicit social differences without explicit prompts. Focusing on high-context Chinese interactions, we identify a robust phenomenon termed Social Agnosia, where LLMs fail to adequately perceive and accommodate implicit social power, affective arousal, and epistemic status during natural interaction. To diagnose this behavior, we propose C-ISA, a framework grounded in Communication Accommodation Theory that decomposes social adaptation into three approximately orthogonal dimensions, and conduct controlled comparisons across multiple Chinese LLMs under implicit and explicit conditions. Results show that while models substantially adjust linguistic strategies under explicit conditioning, they exhibit socially insensitive and homogenized responses in natural interaction, revealing a structural gap between spontaneous behavior and conditioned capability. The C-ISA dataset is publicly available at https://github.com/ty373/C-ISA.
Instruction-following is a fundamental ability of Large Language Models (LLMs), requiring their generated outputs to follow multiple constraints imposed in input instructions. Numerous studies have attempted to enhance this ability through preference optimization or reinforcement learning based on reward signals from LLM-as-a-Judge. However, existing evaluation models for instruction-following still possess many deficiencies, such as substantial costs and unreliable assessments. To this end, we propose IF-CRITIC, an LLM critic for fine-grained, efficient, and reliable instruction-following evaluation. We first develop a checklist generator to decompose instructions and generate constraint checklists. With the assistance of the checklists, we collect high-quality critique training data through a multi-stage critique filtering mechanism and employ a constraint-level preference optimization method to train IF-CRITIC. Extensive experiments show that the evaluation performance of IF-CRITIC can beat strong LLM-as-a-Judge baselines, including o4-mini and Gemini-3-Pro. With the reward signals provided by IF-CRITIC, LLMs can achieve substantial performance gains in instruction-following optimization under lowercomputational overhead compared to strong LLM critic baselines. Our code and model are available at https://github.com/thu-coai/IF-CRITIC.
Large language model (LLM) personalization aims to adapt general-purpose models to individual users. Most existing methods, however, are developed under data-rich and resource-abundant settings, often incurring privacy risks. In contrast, realistic personalization typically occurs after deployment under (i) extremely limited user data, (ii) constrained computational resources, and (iii) strict privacy requirements. We propose PRISP, a lightweight and privacy-safe personalization framework tailored to these constraints. PRISP leverages a Text-to-LoRA hypernetwork to generate task-aware LoRA parameters from task descriptions, and enables efficient user personalization by optimizing a small subset of task-aware LoRA parameters together with minimal additional modules using few-shot user data. Experiments on a few-shot variant of the LaMP benchmark demonstrate that PRISP achieves strong overall performance compared to prior approaches, while reducing computational overhead and eliminating privacy risks.
CharTide: Data-Centric Chart-to-Code Generation via Tri-Perspective Tuning and Inquiry-Driven Evolution
PDF ↗Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by data-centric limitations: despite the availability of growing chart-to-code datasets, simply scaling homogeneous chart-code pairs conflates visual perception with program logic, preventing models from fully leveraging the richness of multimodal supervision. We present CharTide, a novel data-centric framework that systematically redesigns both training and alignment data for chart-to-code generation. First, we construct a 2M-sample dataset via a Tri-Perspective Tuning strategy, explicitly decoupling training into visual perception, pure-text code logic, and modality fusion streams, enabling a 7B model to surpass specialized baselines using only supervised data. Second, we reformulate alignment as a data verification problem rather than a heuristic scoring task. To this end, we introduce an Inquiry-Driven RL framework grounded in the principle of information invariance: a downstream model should yield consistent answers to identical visual queries across both original and generated charts. Moving beyond rigid rule matching or VLM scoring, we employ a frozen Inspector to objectively verify generated charts through atomic QA tasks, providing verifiable reward signals based on answer accuracy. Experiments on ChartMimic, Plot2Code, and ChartX show that CharTide-7B/8B significantly outperforms open-source baselines, surpasses GPT-4o, and is competitive with GPT-5.
Continual learning (CL) for large language models (LLMs) aims to enable sequential knowledge acquisition without catastrophic forgetting. Memory replay methods are widely used for their practicality and effectiveness, but most rely on fixed, step-based heuristics that often misalign with the model’s actual learning progress, since identical training steps can result in varying degrees of parameter change. Motivated by recent findings that LLM forgetting mirrors the Ebbinghaus human forgetting curve, we propose FOREVER (FORgEtting curVe-inspired mEmory Replay), a novel CL framework that aligns replay schedules with a model-centric notion of time. FOREVER defines model time using the magnitude of optimizer updates, allowing forgetting curve-inspired replay intervals to align with the model’s internal evolution rather than raw training steps. Building on this approach, FOREVER incorporates a forgetting curve-based replay scheduler to determine when to replay and an intensity-aware regularization mechanism to adaptively control how to replay. Extensive experiments on three CL benchmarks and models ranging from 0.6B to 13B parameters demonstrate that FOREVER consistently mitigates catastrophic forgetting.
Debate has emerged as a promising oversight mechanism for Large Language Models (LLMs) amid rising systemic complexity, particularly where models outperform human evaluators. Yet, Debate provides little verifiable evidence for its final judgments, and its scalability remains largely unexplored. To make oversight grounded and scale as capabilities extend, we introduce an Agentic Oversight framework. By using Dialectic Argumentation as a reasoning function, we extend this paradigm to multilingual and multimodal spaces. We employ a weak-to-strong oversight approach based on two expert models that evaluate and defend contesting answers, while a third blind judge determines the winner using Dialectic Argumentation. Experts argue only for belief-consistent answers, founding the Debate on disagreements. We experimented with six tasks on our framework in both multilingual and multimodal scenarios, and dialectic argumentation consistently outperforms single-expert baselines. Moreover, we show that dialectic judgements from a weaker model deliver argument-mediated supervision that, via fine-tuning, instils unsupervised reasoning signals in expert models.
Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that contradicts the visual input. Existing research has primarily focused on mitigating object hallucinations, but often overlooks more complex relation hallucinations, particularly action relations involving interactions between objects. In this study, we empirically observe that the primary cause of action-relation hallucinations in LVLMs is the insufficient attention allocated to visual information. Thus, we propose a framework to locate action-relevant image regions and enhance the LVLM’s attention to those regions. Specifically, we define the Action-Relation Sensitivity (ARS) score to identify attention heads that are most sensitive to action-relation changes, thereby localizing action-relevant image regions that contain key visual cues. Then, we propose the Relation-aware Visual Enhancement (RVE) method to enhance the LVLM’s attention to these action-relevant image regions. Extensive experiments demonstrate that, compared to existing baselines, our method achieves superior performance in mitigating action-relation hallucinations with negligible additional inference cost. Furthermore, it effectively generalizes to spatial-relation hallucinations and object hallucinations.
Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning
PDF ↗Amidst a shortage of qualified mental health professionals, the integration of large language models (LLMs) into psychological applications offers a promising way to alleviate the growing burden of mental health disorders. Recent reasoning-augmented LLMs have achieved remarkable performance in mathematics and programming, while research in the psychological domain has predominantly emphasized emotional support and empathetic dialogue, with limited attention to reasoning mechanisms that are beneficial to generating accurate responses. Therefore, in this paper, we propose Psyche-R1, the first Chinese psychological LLM that jointly integrates empathy, psychological expertise, and reasoning, built upon a novel data curation pipeline. Specifically, we design a comprehensive data synthesis pipeline that produces over 75k high-quality psychological questions paired with detailed rationales, generated through and iterative prompt-rationale optimization procedure, along with 73k empathetic dialogues. Subsequently, we employ a hybrid training strategy wherein challenging samples are identified through a multi-LLM cross-selection strategy for group relative policy optimization (GRPO) to improve reasoning ability, while the remaining data are used for supervised fine-tuning (SFT) to enhance empathetic response generation and psychological domain knowledge. Extensive experiment results demonstrate the effectiveness of Psyche-R1 across several psychological benchmarks, where our 7B Psyche-R1 achieves comparable results to 671B DeepSeek-R1.
MED-COREASONER: Reducing Language Disparities in Medical Reasoning via Language-Informed Co-Reasoning
PDF ↗While reasoning-enhanced large language models perform strongly on English medical tasks, a persistent multilingual gap remains, with substantially weaker reasoning in local languages, limiting equitable global medical deployment. To bridge this gap, we introduce Med-CoReasoner, a language-informed co-reasoning framework that elicits parallel English and local-language reasoning, abstracts them into structured concepts, and integrates local clinical knowledge into an English logical scaffold via concept-level alignment and retrieval. This design combines the structural robustness of English reasoning with the practice-grounded expertise encoded in local languages. To evaluate multilingual medical reasoning beyond multiple-choice settings, we construct MultiMed-X, a benchmark covering seven languages with expert-annotated long-form question answering and natural language inference tasks, comprising 350 instances per language. Experiments across three benchmarks show that Med-CoReasoner improves multilingual reasoning performance by an average of 5%, with particularly substantial gains in low-resource languages. Moreover, model distillation and expert evaluation analysis further confirm that Med-CoReasoner produces clinically sound and culturally grounded reasoning traces.
A central goal of LLM alignment is to balance helpfulness with harmlessness, yet these objectives conflict when the same knowledge serves both legitimate and malicious purposes. This tension is amplified by context-sensitive alignment: we observe that domain-specific contexts (e.g., chemistry) selectively relax defenses for domain-relevant harmful knowledge, while safety-research contexts (e.g., jailbreak studies) trigger broader relaxation spanning all harm categories. To systematically exploit this vulnerability, we propose Jargon, a framework combining safety-research contexts with multi-turn adversarial interactions that achieves attack success rates exceeding 93% across seven frontier models, including GPT-5.2, Claude-4.5, and Gemini-3, substantially outperforming existing methods. Activation space analysis reveals that Jargon queries occupy an intermediate region between benign and harmful inputs, a gray zone where refusal decisions become unreliable. To mitigate this vulnerability, we design a policy-guided safeguard that steers models toward helpful yet harmless responses, and internalize this capability through alignment fine-tuning, reducing attack success rates while preserving helpfulness.
Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering
PDF ↗Large Language Models (LLMs) and Large Vision-Language Models (LVLMs) demonstrate strong reasoning capabilities, yet their performance in English significantly outperforms that in low-resource languages, raising fairness concerns in multilingual applications. Existing approaches either rely on costly multilingual training or employ prompting with external translation tools, both of which are resource-intensive and sensitive to translation quality. To address these limitations, we propose a training-free inference-time method to enhance Multilingual Reasoning capabilities via Representation Engineering (MRRE) without using any additional training data or tools. MRRE sequentially injects two precomputed vectors at specific layers during inference processing: cross-lingual reasoning enhancement vectors, which steer non-English reasoning representations toward English space to unlock multilingual reasoning, and target-language output anchoring vectors, which restore the distribution of the target language to preserve input–output language consistency. Comprehensive experiments across six advanced LLMs and LVLMs on four reasoning benchmarks demonstrate that MRRE consistently enhances non-English reasoning by an average gain of 5.48% and up to 7.54% in low-resource languages (e.g., Thai and Swahili), while improving input-output language consistency by 3.78%.
GeoLaux: A Benchmark for Evaluating MLLMs’ Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
PDF ↗Geometry problem solving (GPS) poses significant challenges for Multimodal Large Language Models (MLLMs) in diagram comprehension, knowledge application, long-step reasoning, and auxiliary line construction. However, current benchmarks lack fine-grained evaluation for long-step problems necessitating auxiliary construction. To address these limitations, we present GeoLaux, a fine-grained annotated dataset comprising 2186 calculation and proof problems. It features long-step reasoning (with an average solution length of 6.51 steps, maximum of 24 steps) and auxiliary line construction (required in 41.8% of problems). Building on the dataset, we conduct a comprehensive five-dimensional evaluation of 23 leading MLLMs. The evaluation yields three pivotal findings: First, models perform significantly worse on long-step problems compared to short-step ones, with 18 models exhibiting a performance drop of over 50%. Second, it is crucial to enhance models’ understanding, awareness, and proficiency in auxiliary line construction, which is vital for overall geometric reasoning. Third, limited answer hints effectively improve process correctness, whereas explicit answers lead models to neglect intermediate reasoning steps. These findings position GeoLaux both to benchmark MLLMs geometry reasoning abilities and to guide their improvement. Data and code are available at https://github.com/Candice-yu/GeoLaux
PARIF: Pushing the Pareto Frontier of Instruction Following and Reasoning with Curriculum Reinforcement Learning
PDF ↗Large Reasoning Models (LRMs) excel at complex problem-solving but frequently overlook specific instruction constraints. Existing alignment methods struggle to balance general reasoning with instruction-following (IF), hindered by dependency on teacher models, reward hacking, and reasoning-answer inconsistencies. We propose PARIF, a two-stage curriculum learning framework based on Reinforcement Learning from Verifiable Rewards (RLVR) to enhance both IF and general reasoning capabilities. The framework employs a correctness proxy across different stages to mitigate reward hacking. Stage I employs a dynamic weighting strategy simultaneously to optimize the model’s reasoning paradigm regarding constraints. Stage II introduces Decoupled-GRPO, which builds upon the first stage to enhance the logical consistency between the reasoning process and the final answer, enabling the model to better leverage its optimized reasoning paradigm. To support the framework, we curate 26,000 high-quality instructions featuring diverse constraints. Extensive experiments demonstrate PARIF’s effectiveness: our 7B model achieves a remarkable 21.25% relative average improvement to the original model across six representative IF tasks, while our 8B model outperforms leading models like DeepSeek-V3 on these IF tasks, effectively pushing the Pareto frontier of instruction following and reasoning for models of comparable scale. We open-source our code and models to facilitate future research.
Federated Retrieval (FR) routes queries across multiple external knowledge sources, to mitigate hallucinations of LLMs, when necessary external knowledge is distributed. However, existing methods struggle to retrieve high-quality and relevant documents for ambiguous queries, especially in cross-domain scenarios, which significantly limits their effectiveness in supporting downstream generation tasks. Inspired by Dynamic Information Flow (DIF), we propose DFAMS, a novel framework that leverages DIF to identify latent query intents and construct semantically aligned knowledge partitions for accurate retrieval across heterogeneous sources. Specifically, DFAMS probes the DIF in LLMs by leveraging gradient signals from a few annotated queries and employing Shapley value-based attribution to trace neuron activation paths associated with intent recognition and subdomain boundary detection. Then, DFAMS leverages DIF to train an alignment module via multi-prototype contrastive learning, enabling fine-grained intra-source modeling and inter-source semantic alignment across knowledge bases. Experimental results across five benchmarks show that DFAMS outperforms advanced FR methods by up to 14.37% in knowledge classification accuracy, 5.38% in retrieval recall, and 6.45% in downstream QA accuracy, demonstrating its effectiveness in complex FR scenarios. Our code is publicly available at https://github.com/Artessay/DFAMS.
BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers?
PDF ↗The convergence of LLM-powered research assistants and AI-based peer review systems creates a critical vulnerability: fully automated publication loops where AI-generated research is evaluated by AI reviewers without human oversight. We investigate this through BadScientist, a framework that evaluates whether fabrication-oriented paper generation agents can deceive multi-model LLM review systems. Our generator employs presentation-manipulation strategies requiring no real experiments. We develop a rigorous evaluation framework with formal error guarantees (concentration bounds and calibration analysis), calibrated on real data. Our results reveal systematic vulnerabilities: fabricated papers achieve acceptance rates up to 82%. Critically, we identify concern-acceptance conflict—reviewers frequently flag integrity issues yet assign acceptance-level scores. Our mitigation strategies show only marginal improvements, with detection accuracy barely exceeding random chance. Despite provably sound aggregation mathematics, integrity checking systematically fails, exposing fundamental limitations in current AI-driven review systems and underscoring the urgent need for defense-in-depth safeguards in scientific publishing.