Multimodal Large Language Models (MLLMs) are making significant progress in multimodal reasoning. Early approaches focus on pure text-based reasoning. More recent studies have incorporated multimodal information into the reasoning steps; however, they often follow a single task-specific reasoning pattern, which limits their generalizability across various multimodal tasks. In fact, there are numerous multimodal tasks requiring diverse reasoning skills, such as zooming in on a specific region or marking an object within an image. To address this, we propose unified generative multimodal reasoning, which unifies diverse multimodal reasoning skills by generating intermediate images during the reasoning process. We instantiate this paradigm with Omni-R1, a two-stage SFT+RL framework featuring perception alignment loss and perception reward, thereby enabling functional image generation. Additionally, we introduce Omni-R1-Zero, which eliminates the need for multimodal annotations by bootstrapping step-wise visualizations from text-only reasoning data. Empirical results show that Omni-R1 achieves unified generative reasoning across a wide range of multimodal tasks, and Omni-R1-Zero can match or even surpass Omni-R1 on average, suggesting a promising direction for generative multimodal reasoning. The code and checkpoints are attached for reproducibility and subsequent open release.
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
Reasoning-oriented language models typically expose explicit reasoning as a long, front-loaded chain of “thinking” tokens before the main output, either always enabled or externally toggled at inference time. Although this can help on arithmetic, coding, and other multi-step tasks, it is costly, weakens claim-level auditability, and does not allow the model to re-trigger explicit reasoning once presentation has begun. In dialogue, these limitations are compounded by weak sensitivity to temporal structure: unless time is explicitly stated in text, standard models treat replies separated by seconds and replies separated by weeks as equivalent. We introduce TIME (Temporally Intelligent Meta-reasoning Engine), a behavioral alignment framework that learns explicit reasoning as a context-triggered control policy rather than a fixed response mode. TIME augments dialogue with optional ISO 8601 ‘<time>‘ tags, tick events that represent silent time passage, and short ‘<think>‘ blocks that may appear anywhere in a response. Using a four-phase curriculum, including a small maximally diverse full-batch alignment stage, we train Qwen3 dense models to invoke brief, in-place reasoning bursts only when contextual cues warrant them, while keeping user-facing output compact. We also introduce TIMEBench, a diagnostic benchmark for evaluating reasoning from temporal cues in dialogue. Across 4B-32B scales, TIME improves TIMEBench scores over the corresponding base Qwen3 models in both thinking and no-thinking modes while reducing explicit reasoning tokens by roughly an order of magnitude. Beyond score improvements, TIME induces a distinct behavioral shift: explicit reasoning becomes more compact and more responsive to contextual cues. Code, training data, and benchmark artifacts are publicly available.
Parametric Knowledge is Not All You Need: Toward Honest Large Language Models via Retrieval of Pretraining Data
PDF ↗Large language models (LLMs) are highly capable of answering questions, but they are often unaware of their own knowledge boundary, i.e., knowing what they know and what they don’t know. As a result, they can generate factually incorrect responses on topics they do not have enough knowledge of, commonly known as hallucination. Rather than hallucinating, a language model should be more honest and respond with "I don’t know" when it does not have enough knowledge about a topic. Many methods have been proposed to improve LLM honesty, but their evaluations lack robustness, as they do not take into account the knowledge that the LLM has ingested during its pretraining. In this paper, we propose a more robust evaluation benchmark dataset for LLM honesty by utilizing Pythia, a truly open LLM with publicly available pretraining data. In addition, we also propose a novel method for harnessing the pretraining data to build a more honest LLM.
Current financial benchmarks prioritize large language models (LLMs) for task accuracy and portfolio returns, yet overlook risks arising from multi-agent cooperation, tool-sharing, and real-world financial actions. We introduce M-SAEA, a Multi-agent, Safety-Aware Evaluation Agent that audits LLM teams without fine-tuning, deploying ten probes across four layers: model, workflow, interaction, and system, to yield a continuous risk vector and natural-language rationale. Evaluated across three high-stakes tasks (finance management, webshop automation, transactional services) with six prominent models, M-SAEA (i) identifies unsafe trajectories with minimal false positives, (ii) reveals latent risks (e.g., temporal staleness) that are not addressed by standard metrics, and (iii) provides granular, actionable scores for balancing safety and latency pre-deployment. By quantifying safety as a model-agnostic metric, M-SAEA reorients evaluation from individual tasks to collaborative teams, offering a robust template for risk-first assessment of agentic AI in finance and beyond.
Human visual reasoning typically follows a coarse-to-fine attention process, starting from global scene understanding and gradually focusing on question-relevant regions. However, multimodal large language models may deviate from this pattern due to attention drift and the underutilization of visual evidence, which can lead to hallucinations. To mitigate these issues, this study proposes a Dual-Indicator Guided Contrastive Alignment (DICA), which tracks two information-theoretic indicators during inference: Visual Attention Entropy (VAE), which reflects the concentration of visual attention, and Output Image Correlation (OIC), which measures the dependence of generated outputs on the visual input. An abnormal increase in VAE or a decrease in OIC corresponds to different failure modes, which trigger targeted contrastive alignment to restore visual grounding. Experimental results across multiple benchmarks demonstrate that DICA consistently outperforms existing approaches and substantially reduces hallucinations, highlighting the effectiveness of indicator-driven intervention in improving multimodal inference reliability. The code is publicly available at https://github.com/BGWH123/DICA/.
We study ambiguous-query disambiguation in retrieval-augmented generation (RAG). Prior Diversify-then-Verify (DtV) pipelines first generate interpretations and then retrieve evidence, often introducing ungrounded queries that cannot be answered from the corpus and requiring costly post-hoc pruning and verification. We propose VerDICT, a novel approach that unifies diversification with verification by integrating retriever relevance and generator answerability feedback early. This not only reduces cascading errors but also enables parallelism. On ASQA, VerDICT improves grounding-aware F1 by an average of 23% over the strongest baselines across multiple LLM backbones.
Poetry has long been a central art form for Arabic speakers, serving as a powerful medium of expression and cultural identity. While modern Arabic speakers continue to value poetry, existing research on Arabic poetry within Large Language Models (LLMs) has primarily focused on analysis tasks such as interpretation or metadata prediction, e.g., rhyme schemes and titles. In contrast, our work addresses the practical aspect of poetry creation in Arabic by introducing controllable generation capabilities to assist users in writing poetry. Specifically, we present a large-scale, carefully curated instruction-based dataset in Modern Standard Arabic (MSA) and various Arabic dialects. This dataset enables tasks such as writing, revising, and continuing poems based on predefined criteria, including style and rhyme, as well as performing poetry analysis. Our experiments show that fine-tuning LLMs on this dataset yields models that can effectively generate poetry that is aligned with user requirements, based on both automated metrics and human evaluation with native Arabic speakers. The data and the code are available at https://github.com/mbzuai-nlp/instructpoet-ar
Scaling test-time compute via Long Chain-of-Thought (Long-CoT) significantly enhances reasoning capabilities, yet extended generation does not guarantee correctness: after an early wrong commitment, models may keep elaborating a self-consistent but incorrect prefix. Through fine-grained trajectory analysis, we identify Thinking Traps, prefix-dominant deadlocks where later reflection, alternative attempts, or verification fails to revise the root error. On a curated subset of DAPO-MATH, 89% of failures exhibit such traps. To solve this problem, we introduce TAAR (Trap-Aware Adaptive Restart), a test-time control framework that trains a diagnostic policy to predict two signals from partial trajectories: a trap index for where to truncate and an escape probability for whether and how strongly to intervene. At inference time, TAAR truncates the trajectory before the predicted trap segment and adaptively restarts decoding; for severely trapped cases, it applies stronger perturbations, including higher-temperature resampling and an optional structured reboot suffix. Experiments on challenging mathematical and scientific reasoning benchmarks (AIME24, AIME25, GPQA-Diamond, HMMT25, BRUMO25) show that TAAR improves reasoning performance without fine-tuning base model parameters.
All Prompts Are Created Equal? Evaluating Robustness of LLM Judges Against Non-Adversarial Prompt Variations
PDF ↗LLM-based evaluation systems (LLM judges) have emerged as a scalable alternative to expensive human evaluations. Although LLM judges demonstrate 70-80% agreement with human evaluators, their robustness under semantically equivalent prompt variations remains underexplored. Through systematic evaluation of 8 models across 4 NLG tasks using 10 semantically equivalent paraphrases per prompt (~115000 evaluations), we identify a critical accuracy-robustness gap: attribute verifiability affects the robustness more than model choice, with factually verifiable attributes achieving 0.71 accuracy versus 0.19 for subjective attributes. Our investigations discover three key insights: 1) Task structure characteristics influence the robustness and in turn accuracy, 2) Attribute verifiability as the strongest predictor-factually verifiable attribute achieve 0.71 accuracy versus 0.19 for subjective attributes, 3) No single winning model-smallest model (Llama-3.1-8B) exhibits second-best performance, while the strongest model (Llama-4) from the same family significantly lag behind, thus demonstrating that general capability improvements do not necessarily result in evaluation robustness. With these findings, we propose a diagnostic framework grounded in attribute verifiability that enables principled decisions about evaluation automation. Our work establishes new standards for assessing LLM judge reliability beyond simple accuracy metrics.
Generating spoken dialogue is inherently more complex than monologue text-to-speech (TTS), as it demands both realistic turn-taking and the maintenance of distinct speaker timbres. While existing autoregressive (AR) models have made progress, they often suffer from high inference latency and stability issues. To overcome these limitations, we propose ZipVoice-Dialog, a non-autoregressive (NAR) zero-shot spoken dialogue generation model based on flow-matching. Observing that applying vanilla flow-matching to dialogue generation leads to poor speech intelligibility and turn-taking precision, we introduce two simple yet effective methods to adapt flow-matching architectures for dialogue generation: (1) a curriculum learning strategy to ensure robust speech-text alignment, and (2) speaker-turn embeddings to govern precise speaker turn-taking. Additionally, we introduce dedicated strategies to support stereo dialogue generation.Recognizing the lack of training datasets in this field, we curate and release OpenDialog, the first large-scale (6.8k hours) open-source spoken dialogue dataset derived from in-the-wild speech data. Moreover, for fair and rigorous evaluations, we established a benchmark to comprehensively evaluate dialogue generation models. Experiments demonstrate the effectiveness of the proposed methods and dataset, showing that ZipVoice-Dialog achieves superior performance in inference speed, intelligibility, speaker turn-taking accuracy, and speaker similarity. Our code, model checkpoints, and the OpenDialog dataset are publicly available.
Uncertainty-Aware Contrastive Sentence Embedding With Local Context Representation for Text Classification
PDF ↗In real-world applications of natural language processing, it is essential to effectively adapt a pre-trained model to a downstream task. While text classification is undertaken as a downstream task, it is crucial to produce meaningful sentence embedding that is adaptive to the task. In this paper, we explore how to effectively adapt a pre-trained model for extracting meaningful context representations from sentences, and propose an uncertainty-aware contrastive sentence embedding approach that involves addressing language ambiguity and inter-class separability for a text classification task. Specifically, we design an end-to-end strategy for driving the process of learning to transform a word embedding matrix into a contextualized sentence vector and to quantify the representation uncertainty of the sentence, while the word embedding matrix is produced by a pre-trained model without fine-tuning, and a label-wise contrastive learning strategy is designed to enhance intra-class compactness and inter-class separability. The results on public data sets show that a considerable improvement of text classification accuracy is achieved by adopting the proposed approach in comparison with using those state-of-the-art methods.
Sparse attention offers a promising strategy to extend long-context capabilities in Transformer LLMs, yet its efficiency–accuracy trade-offs remain unclear due to the lack of comprehensive evaluation. We address this gap with the largest-scale empirical analysis to date of training-free sparse attention, evaluating six methods across multiple model families and sizes, sequences up to 128K tokens, and sparsity levels up to 0.95 (i.e., 1/20 attention budget) on nine diverse tasks. We first organise the rapidly evolving landscape of sparse attention methods into a taxonomy along four design axes. Our analysis then yields actionable insights: 1) sparse attention is effective: larger sparse models outperform smaller dense ones at equivalent cost, improving the Pareto frontier; 2) for the training-free methods we study, fine-grained per-query importance estimation during prefilling remains impractical—due to both the cost of estimation and the lack of sparse kernels that translate fine-grained sparsity into wall-clock gains—forcing a task-dependent choice between global-to-token and block-to-block selection. Instead, during decoding, token-to-page selection becomes feasible, enabling better generalisation and higher sparsity tolerance; 3) longer sequences tolerate higher sparsity, suggesting that fixed-budget methods in production are suboptimal. Together, these findings provide practical guidance for deploying sparse attention and methodological recommendations for future evaluations. Our code is available at https://github.com/PiotrNawrot/sparse-frontier.
Cause-CSD: A Challenge Multimodal Conversational Stance Cause Detection Dataset and Effective Method
PDF ↗Social media platforms have become critical arenas for public discourse, yet existing stance detection methods often reduce opinions to surface-level labels, overlooking the conversational evidence behind stance expressions. We introduce Conversational Stance-Cause Pair Detection (CSCPD), a new task that jointly identifies both the stance polarity and its observable contextual evidence within multi-turn conversations. To advance research in this direction, we present Cause-CSD, the first large-scale dataset for CSCPD, spanning 21,048 annotated stance-cause pairs across diverse open-domain, textual, and multimodal discussions. We further propose Stance-Cause Detection Language Model (SCD-LM), a unified language model framework that leverages explicit context reasoning and joint decoding to predict stances and their supporting causes, along with human-readable rationales. Extensive experiments demonstrate that SCD-LM achieves state-of-the-art results on both text-only and multimodal subtasks, significantly outperforming strong baselines, especially for long-range and image-grounded cause detection. Our work advances explainable stance analysis and underpins understanding of public opinion drivers in impactful online settings.
Agent for Numerical Data Retrieval and Understanding by Code Generation and Multimodal Reasoning
PDF ↗Numerical data from sensors and time series are widely used in scientific research fields such as nuclear fusion experiments, which generate vast amounts of complex, high-dimensional data. Therefore, efficient numerical data analysis tools are crucial to accelerate experimental research. Large language models (LLMs) have emerged as promising solutions to analyze numerical data with natural language queries. However, LLMs have difficulties treating this type of data as they have been designed for text in the first place. To overcome these limitations, we propose a model-agnostic and data-agnostic agent that processes numerical data by code generation and multimodal reasoning. Our agent demonstrates competitive performance against baselines on benchmark data on numerical data tasks such as sensor data classification and time series understanding. While outperforming them on information retrieval benchmarks, also we have successfully applied our agent in the context of nuclear fusion research, where physicists and Tokamak operators interact with it to plan and analyze fusion experiments.
KnowDR-REC: Auditing Knowledge-Conditioned Visual Grounding in Referring Expression Comprehension
PDF ↗While Multimodal Large Language Models (MLLMs) have demonstrated the capacity for multi-modal reasoning, current Referring Expression Comprehension (REC) benchmarks lag behind, predominantly relying on intra-image cues and neglecting the integration of external world knowledge, which significantly impedes the evolution of REC towards real-world applications. This limitation obscures a model’s true capability to conduct textual reasoning (entity resolution), resolve spatial location (visual grounding), and verify reference validity (hallucination rejection). To address this, we introduce KnowDR-REC, a targeted audit benchmark comprising 1,042 positive triplets derived from real-world knowledge, along with rigorously matched negative samples. Unlike traditional datasets, we implement a controllable counterfactual evaluation mechanism that subjects textual expressions to single-factor perturbations (entity, relation, or time) to test sensitivity to fine-grained factual changes. Extensive evaluation of 18 state-of-the-art LMMs exposes a critical “binding hallucination,” revealing that current high performance is often built on fragile visual shortcuts rather than true understanding. KnowDR-REC thus serves as a pivotal diagnostic instrument, steering future research toward the genuine integration of perception and reasoning.
Retrieval-Augmented Generation (RAG) has been widely adopted to enhance large language models (LLMs) by incorporating external knowledge. However, the two main existing paradigms struggle with multi-hop reasoning: aggregate-first approaches suffer from high construction costs and limited adaptability to dynamic knowledge, while dynamic-first approaches rely heavily on LLM reasoning and are prone to error propagation across reasoning steps. To address these limitations, we propose SR-RAG, a symbolic reasoning framework for multi-hop question answering. SR-RAG integrates the advantages of both paradigms by dynamically generating sub-questions, performing information retrieval and symbolic encoding based on an on-the-fly graph, and using a symbolic verifier to formally validate intermediate reasoning steps to ensure the correctness of intermediate answers and the completeness of the reasoning chain . We evaluate SR-RAG on multiple multi-hop benchmarks and a medical dataset. Experimental results demonstrate that it significantly improves both accuracy and robustness.
Large language models exhibit surprising sensitivity to the structure of the prompt, but the mechanisms underlying this sensitivity remain poorly understood. In this work, we conduct an in-depth investigation on a striking case: in multiple-choice question answering, placing context before the questions and options (CQO) outperforms the reverse order (QOC) by over 14%p, consistently over a wide range of models and datasets. Through systematic architectural analysis, we identify causal attention as the core mechanism: in QOC prompts, the causal mask prevents option tokens from attending to context, creating an information bottleneck where context becomes invisible to options.
From Individual Excellence to Collective Sustainability: Seeking Strategic Equilibrium in Proactive Multi-Agent Teams
PDF ↗In heterogeneous scientific teams, proactive team agents can serve as effective assistants regarding the research progress of the project. However, proactive agents always suffer from collaborative myopia: a greedy optimization for immediate task accuracy which ignore the long-term goal of team sustainability. This leads to the Individual-centric Trap, where capable experts (e.g., PIs) are disproportionately overloaded while Junior roles remain underutilized. Therefore, neglecting opportunity costs in task allocation can implicitly erodes the enduring performance of the team. To solve this imbalance between efficiency and sustainability, we propose GT-PMARL (Game-Theoretic Proactive Multi-Agent Reinforcement Learning). By internalizing the opportunity cost as a key consideration in individual decision-making, the collaboration logic of agents has been reshaped. Our framework employs: (1) a Positive-Unlabeled scorer to anchor intervention quality under sparse supervision; (2) a Nash-Pareto competitive objective to seek an equilibrium between individual task excellence and collective load balancing. Empirical experiments in scientific workflows show that GT-PMARL effectively maintains high performance while preventing experts from over-developing. Our work provides a scalable paradigm for building a sustainable and balanced human-AI collaborative ecosystem.
Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare. However, the principles and values that guide these models when distributing scarce societal resources remain largely unexamined. To address this, we introduce the Social Welfare Function (SWF) Benchmark, a dynamic simulation environment in which an LLM acts as a dictator, distributing tasks to heterogeneous recipients with different returns on investment (ROI). The benchmark is designed to create a dilemma between maximizing collective efficiency (i.e., overall ROI) and ensuring distributive fairness (measured by the Gini coefficient). We evaluate 20 state-of-the-art LLMs. Our findings reveal several key insights, including: (i) LLMs’ general ability, as measured by popular Arena leaderboards, misaligns with their allocation skills; (ii) Most LLMs exhibit a strong default utilitarian orientation, prioritizing overall productivity at the expense of inequality. (iii) Allocation behaviors are highly manipulated, easily perturbed by common persuasion strategies. These results highlight the risks of deploying current LLMs as societal decision-makers and underscore the need for specialized benchmarks and alignment for AI governance.
As language models accelerate scientific research by automating hypothesis generation and implementation, a new bottleneck emerges: evaluating and filtering hundreds of AI-generated ideas without exhaustive experimentation. We ask whether LMs can learn to forecast the empirical success of research ideas before any experiments are run. We study comparative empirical forecasting: given a benchmark-specific research goal and two candidate ideas, predict which will achieve better benchmark performance. We construct a dataset of 11,488 idea pairs grounded in objective outcomes from PapersWithCode. While off-the-shelf 8B-parameter models struggle (30% acc.), SFT dramatically boosts performance to 77.1%, outperforming GPT-5 (61.1%). By framing evaluation as a reasoning task via Reinforcement Learning with Verifiable Rewards (RLVR), we train models to discover latent reasoning paths, achieving 71.35% acc. with interpretable justifications. Through additional ablations and out-of-distribution tests, we show robustness to surface-level heuristics and transfer to both a cross-domain time-split test set and an independently constructed test set. Our results demonstrate that compute-efficient small language models can serve as effective, objective verifiers, offering a scalable path for autonomous scientific discovery.