论文检索

Applications · Language, Speech and Dialog

Haohao Luo, Zexi Li, Yuexiang Xie, Wenhao Zhang, Yaliang Li, Ying Shen

Deep Research (DR) agents extend Large Language Models (LLMs) beyond parametric knowledge by autonomously retrieving and synthesizing evidence from large web corpora into long-form reports, enabling a long-horizon agentic paradigm. However, unlike real-time conversational assistants, DR is computationally expensive and time-consuming, creating an autonomy-interaction dilemma: high autonomy on ambiguous user queries often leads to prolonged execution with unsatisfactory outcomes. To address this, we propose IntentRL, a framework that trains proactive agents to clarify latent user intents before starting long-horizon research. To overcome the scarcity of open-ended research data, we introduce a scalable pipeline that expands a few seed samples into high-quality dialogue turns via a shallow-to-deep intent refinement graph. We further adopt a two-stage reinforcement learning (RL) strategy: Stage I applies RL on offline dialogues to efficiently learn general user-interaction behavior, while Stage II uses the trained agent and a user simulator for online rollouts to strengthen adaptation to diverse user feedback. Extensive experiments show that IntentRL significantly improves both intent hit rate and downstream task performance, outperforming the built-in clarify modules of closed-source DR agents and proactive LLM baselines.

General Machine Learning · Evaluation

Yuqi Guo, Siwei Wei, Yan Cai

Large Language Models (LLMs) have demonstrated sophisticated comprehension of sequential code, yet their capacity for reasoning about concurrent programs remains largely unquantified. We introduce DRPBench, a benchmark designed to evaluate the concurrent code comprehension of LLMs by measuring their data race prediction performance. To address the challenge of runtime non-determinism for evaluation on concurrent programs, we frame the evaluation as a fine-grained static prediction task using 1,003 programs from the SV-COMP suite, featuring 549 manually annotated data races with precise variable- and line-level granularity. Our evaluation of 15 state-of-the-art LLMs—spanning standard, reasoning, and agentic variants—reveals that DRPBench effectively differentiates concurrent code comprehension capabilities of LLMs. While the top-performing model (Gemini 3 with test-time reasoning) achieves an F1 score of 74.89%, most models struggle significantly (scoring less than 60%), with Llama 3 70B achieving only 8.80%. Beyond benchmarking, we characterize two primary failure modes: (1) shared-variable distraction, where multiple variable appearances degrade comprehension accuracy, and (2) synchronization-logic myopia, the inability to interpret non-standard synchronization implementations. Our findings provide a diagnostic roadmap for enhancing concurrent code comprehension of LLMs in future development.

Deep Learning · Other Representation Learning

Shuhao Fu, Esther Goldberg, Ying Nian Wu, Hongjing Lu

Large Multimodal Models (LMMs) demonstrate impressive in-context learning abilities from few multimodal demonstrations, yet the internal mechanisms supporting such task learning remain opaque. Building on prior work of Large Language Models, we show that a small subset of attention heads in Large Multimodal Models is responsible for transmitting representations of spatial relations. The activations of these attention heads, termed function vectors, can be extracted and manipulated to alter an LMM’s performance on relational tasks. First, using synthetic and real image datasets, we apply causal mediation analysis to identify attention heads that strongly influence relational predictions, and extract multimodal function vectors that improve zero-shot accuracy at inference time. We further demonstrate that these multimodal function vectors can be fine-tuned with a modest amount of training data, while keeping LMM parameters frozen, to significantly outperform in-context learning baselines. Finally, we show that relation-specific function vectors can be linearly combined to solve analogy problems involving novel and untrained spatial relations, highlighting the strong generalization ability of this approach. Through experiments on two LMMs, including OpenFlamingo and Qwen3-VL, our results show that these models encode spatial relational knowledge within localized internal structures, which can be systematically extracted and optimized, thereby advancing our understanding of model modularity and enhancing control over relational reasoning in LMMs.

Social Aspects · Alignment

Yulong Lin, Pablo Bernabeu-Pérez, Benjamin Arnav, Lennie Wells, Mary Phuong

As language models grow more capable, accurate capability evaluation becomes essential for safety decisions. If models can deliberately underperform on dangerous capability evaluations---a behavior known as \emph{sandbagging}---they may evade safety measures designed for their true capability level. We introduce Cross-Context Consistency (C³), a general framework for unsupervised black-box sandbagging detection that exploits a fundamental asymmetry: when a model truly lacks capability, its confusion manifests consistently across paraphrased questions, but when a capable model feigns incompetence, its strategic choices about \emph{how} to appear weak create detectable inconsistencies. The framework is agnostic to the specific consistency metric and aggregation method; we present a simple instantiation using embedding cosine distance and mean aggregation that requires no training data or model-specific adaptation. We evaluate C³ across prompted and fine-tuned sandbagging scenarios, across instructed and more naturalistic setups, maintaining a classification signal where other black-box methods fail. Our findings show the limitations of existing sandbagging detection methods, and reveal the efficacy of consistency-checking as a detection mechanism for dangerous capabilities.

Deep Learning · Large Language Models

Shumin Wang, Yuexiang Xie, Wenhao Zhang, Yuchang Sun, Yanxi Chen, Yaliang Li, Yanyong Zhang

Entropy serves as a critical metric for measuring the diversity of outputs generated by large language models (LLMs), providing valuable insights into their exploration capabilities. While recent studies increasingly focus on monitoring and adjusting entropy to better balance exploration and exploitation in reinforcement fine-tuning (RFT), a principled understanding of entropy dynamics during this process is yet to be thoroughly investigated. In this paper, we establish a theoretical framework for analyzing the entropy dynamics during the RFT process, which begins with a discriminant expression that quantifies entropy change under a single logit update. This foundation enables the derivation of a first-order expression for entropy change, which can be further extended to the update formula of Group Relative Policy Optimization (GRPO). The corollaries and insights drawn from the theoretical analysis inspire the design of entropy control methods, and also offer a unified lens for interpreting various entropy-based methods in existing studies. We provide empirical evidence to support the main conclusions of our analysis and demonstrate the effectiveness of the derived entropy-discriminator clipping methods. This study yields novel insights into RFT training dynamics, providing theoretical support and practical strategies for optimizing the exploration-exploitation balance during LLM fine-tuning.

Social Aspects · Safety

Jaylen Jones, Zhehao Zhang, Yuting Ning, Eric Fosler-Lussier, Pierre-Luc St-Charles, Yoshua Bengio, Dawn Song, Yu Su, Huan Sun

Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from expected outcomes even under benign input contexts. However, exploration of this risk remains largely anecdotal, lacking concrete characterization and automated methods to proactively surface long-tail unintended behaviors under realistic CUA scenarios. To fill this gap, we introduce the first conceptual and methodological framework for unintended CUA behaviors, by defining their key characteristics, automatically eliciting them, and analyzing how they arise from benign inputs. We propose AutoElicit: an agentic framework that iteratively perturbs benign instructions using CUA execution feedback, and elicits severe harms while keeping perturbations realistic and benign. Using AutoElicit, we surface hundreds of harmful unintended behaviors from state-of-the-art CUAs such as Claude 4.5 Haiku and Opus. We further evaluate the transferability of human-verified successful perturbations, identifying persistent susceptibility to unintended behaviors across various other frontier CUAs. This work establishes a foundation for systematically analyzing unintended behaviors in realistic computer-use settings.

Deep Learning · Foundation Models

Jana Zeller, Thaddäus Wiedemer, Fanfei Li, Thomas Klein, Prasanna Mayilvahanan, Matthias Bethge, Felix Wichmann, Ryan Cotterell, Wieland Brendel

Frontier models are transitioning from _multimodal large language models_ (MLLMs) that merely ingest visual information to _unified multimodal models_ (UMMs) capable of native interleaved generation. This shift has sparked interest in using intermediate visualizations as a reasoning aid, akin to human _mental imagery_. Central to this idea is the ability to form, maintain, and manipulate visual representations in a goal-oriented manner. To evaluate and probe this capability, we develop MentisOculi, a procedural, stratified suite of multi-step reasoning problems amenable to visual solution, tuned to challenge frontier models. Evaluating visual strategies ranging from latent tokens to explicit generated imagery, we find they generally fail to improve performance. Analysis of UMMs specifically exposes a critical limitation: While they possess the textual reasoning capacity to solve a task and can sometimes generate correct visuals, they suffer from compounding generation errors and fail to leverage even ground-truth visualizations. Our findings suggest that despite their inherent appeal, _visual thoughts do not yet benefit model reasoning_. MentisOculi establishes the necessary foundation to analyze and close this gap across diverse model families.

Social Aspects · Safety

Arkadiy Saakyan, Charvi Rastogi, Lora Aroyo

Safe global deployment of AI models requires alignment with pluralistic human values, yet in existing safety evaluation datasets the rater pools remain largely homogeneous along geo-cultural dimensions. Through a meta-analysis of existing safety datasets, we observe that the vast majority does not include any geo-cultural information, and the ones that do, lack a robust approach to collect and understand cultural differences in safety ratings. Using the Inglehart-Welzel dimensions of cross-cultural variation, we demonstrate via hierarchical linear modeling that geo-cultural values predict safety ratings significantly better than demographic factors alone ($p<0.05$ in $6$ datasets). Further, our analysis shows that several safety datasets contain at least 10\% of culturally-sensitive items, where lack of cultural representation in the rater pool would lead to a false negative in safety classification. Finally, we provide empirical evidence that fine-tuned LLMs can identify culturally sensitive items but are not reliable at emulating judgments of raters from diverse cultural backgrounds, underscoring the critical need for continuous geo-culturally stratified (pluralistic) safety evaluations.

Social Aspects · Safety

pengcheng li, Jie Zhang, Tianwei Zhang, Han Qiu, Zhang kejun, Weiming Zhang, Nenghai Yu, Wenbo Zhou

Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically effective, the structure of conversational safety failure remains insufficiently understood. In this work, we study safety failures from a state-space perspective and show that many multi-turn failures arise from structured contextual state evolution rather than isolated prompt vulnerabilities. We introduce STAR, a state-oriented diagnostic framework that treats dialogue history as a state transition operator and enables controlled analysis of safety behavior along interaction trajectories. Rather than optimizing attack strength, STAR provides a principled probe of how aligned models traverse the safety boundary under autoregressive conditioning. Across multiple frontier language models, we find that systems which appear robust under static evaluation can undergo rapid and reproducible safety collapse under structured multi-turn interaction. Mechanistic analysis reveals monotonic drift away from refusal-related representations and abrupt phase transitions induced by role-conditioned context. Together, these findings motivate viewing language model safety as a dynamic, state-dependent process defined over conversational trajectories.

Social Aspects · Safety

William Overman, Mohsen Bayati

Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain meaningful oversight of systems that may exceed human capabilities? While scalable oversight is widely studied, existing approaches often rely on complex assumptions, remain largely heuristic, or lack practical methods for sequential settings with statistical guarantees. We introduce Calibrated Collective Oversight (CCO), which aggregates diverse auxiliary scoring functions into a penalty that measures deviation from a conservative baseline. Inspired by Attainable Utility Preservation, CCO enables collective conservatism: when multiple oversight signals register concern, the agent defers. CCO calibrates this conservatism online using Conformal Decision Theory, ensuring that undesirable outcomes remain below a user-specified target $\alpha$ with finite-time bounds and no distributional assumptions. Experiments on SWE-bench demonstrate that weaker overseers successfully constrain an adversarially misaligned stronger agent. Similarly, on MACHIAVELLI, CCO achieves substantial reductions in ethical violations while preserving reward. In both settings, empirical violation rates closely match the specified targets. Our work demonstrates that combining penalty-based conservatism with online calibration yields practical oversight with statistical guarantees suited for agentic deployment.

Applications · Language, Speech and Dialog

Sang-Hoon Lee, Ha-Yeong Choi

Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity. To address this issue, we propose ReGen, a hierarchical multi-prompt representation generation framework that jointly estimates multiple vector fields for both representations and data within a single diffusion model. We further introduce generalized flow matching (GFM) to improve the generalization of conditional flow matching (CFM). We validate ReGen on single-stage waveform diffusion models including neural audio codec and Wave-VAE. ReGen significantly improves waveform generation quality from highly compressed latent representations at 12.5 Hz. We also present ReGenVoice, a latent diffusion model (LDM)-based text-to-speech model that achieves strong speech intelligibility (WER) and speaker similarity (SIM) with a small dataset. Moreover, operating the LDM at 6.25 Hz with rich semantic and acoustic latent representation enables efficient training and sampling, requiring only 1 day of training on 4 GPUs and fast inference with an RTF of 0.08.

Social Aspects · Safety

Maya Okawa

Multi-agent LLM debates achieve strong performance on decision-making tasks as well as problem-solving benchmarks, yet their safety and fairness risks remain poorly understood. Notably, interaction can amplify the biases of single LLMs, raising concerns for real-world deployment. We identify the emergence of collective (often biased) norms in multi-agent LLM debates and show that noise (e.g., LLM sampling temperature) is a key driver. To explain this, we propose an analytical framework drawing on physics-inspired theoretical models of social dynamics. We predict a phase transition to collective bias when conformity surpasses a critical threshold given the LLMs' initial bias and debate noise. We test the theoretical predictions through controlled experiments and observe a finite-size crossover consistent with an underlying phase transition. We further find that agent heterogeneity suppresses emergence by smoothing (rounding) this transition. Finally, we show that these insights generalize to realistic decision-making tasks, including investment decisions and LLM-as-a-judge evaluation.

Deep Learning · Generative Models and Autoencoders

Abdelhakim Ziani, Andras Horvath, Paolo Ballarini

Heavy-tailed distributions are ubiquitous in real-world data, where rare but extreme events dominate risk and variability. However, standard Variational Autoencoders (VAEs) employ simple decoder distributions (e.g., Gaussian) that fail to capture heavy-tailed behavior, while existing heavy-tail-aware extensions remain restricted to predefined parametric families whose tail behavior is fixed a priori. We propose the *Phase-Type Variational Autoencoder* (PH-VAE), whose decoder distribution is a latent-conditioned Phase-Type (PH) distribution—defined as the absorption time of a continuous-time Markov chain (CTMC). This formulation composes multiple exponential time scales, yielding a flexible, analytically tractable decoder that adapts its tail behavior directly from the observed data. Experiments on synthetic and real-world benchmarks demonstrate that PH-VAE accurately recovers diverse heavy-tailed distributions, significantly outperforming Gaussian, Student-t, and extreme-value-based VAE decoders in modeling tail behavior and extreme quantiles. In multivariate settings, PH-VAE captures realistic cross-dimensional tail dependence through its shared latent representation. To our knowledge, this is the first work to integrate Phase-Type distributions into deep generative modeling, bridging applied probability and representation learning.

Social Aspects · Safety

Xiao Wang, Yifei Zhang, Yongkang Liu, Xiaocui Yang, Zihan Wang, Shi Feng, Daling Wang

Safety alignment of Large Language Models (LLMs) is extremely fragile, fine-tuning on small number of benign samples can erase safety behaviors learned from millions of preference examples. Existing studies attempt to explain this phenomenon by comparing parameters and hidden states before and after fine-tuning, but overlook their dynamic evolution during fine-tuning. In this work, we analyze parameter dynamics and uncover a critical mechanism underlying safety degradation, where benign fine-tuning causes parameters cumulatively drift toward danger-aligned directions, progressively undermining the model's safety. Inspired by these findings, we propose Sample-Level Quantification of Safety Degradation (SQSD), a method that quantifies each training sample's influence on safety degradation. Specifically, SQSD assigns continuous risk scores to individual samples by measuring their induced parameter updates along safety and danger directions. Extensive experiments across three models and two datasets show that SQSD outperforms baselines in better separating high-risk and low-risk samples, with risk scores that consistently predict the severity of safety degradation. In particular, SQSD exhibits strong transferability across architectures, parameter scales, and parameter-efficient methods.

Deep Learning · Generative Models and Autoencoders

Junyu Zhang, Daochang Liu, Younghyun Kim, Jong Hwan Ko, Shichao Zhang, Chang Xu, Eunbyung Park

Flow map matching (FMM) enables one- and few-step sampling for diffusion-style generation, yet its performance is often hindered by the mismatch between ground-truth training transitions and model-induced flow maps. We propose \textbf{Contrastive Flow Map Matching (CFMM)}, a principled framework that explicitly aligns FMM training with practical sampling. Our approach is grounded in a theoretical upper bound on the reverse KL divergence, which decomposes the distributional gap into a marginal mismatch over intermediate states and a conditional mismatch in endpoint reconstruction. This analysis motivates two complementary objectives: average-velocity regression for marginal alignment and a sampling-aligned InfoNCE contrastive loss for conditional refinement. CFMM is a training-only plug-in for pre-trained FMMs, incurs no inference-time overhead, and supports training FMMs from scratch. Experiments on CIFAR-10, ImageNet, and LSUN across multiple FMM baselines demonstrate consistent improvements in fidelity and perceptual quality with only modest additional training cost.

Social Aspects · Privacy

Fengyu Gao, Jing Yang

Preference alignment is a crucial post-training step for large language models (LLMs) to ensure their outputs align with human values. However, post-training on real human preference data raises privacy concerns, as these datasets often contain sensitive user prompts and human judgments. To address this, we propose **DPPrefSyn**, a novel algorithm for generating differentially private (DP) synthetic preference data to enable privacy-preserving preference alignment. DPPrefSyn is a principled framework grounded in the Bradley–Terry preference model and the intrinsic geometric structure of pairwise human preference data. It first learns an underlying preference model from private data with formal differential privacy guarantees, and then leverages the learned model together with public prompts to synthesize high-quality preference data. It exploits the shared linear structure of per-cluster reward models to effectively capture heterogeneous human preferences in private datasets, and leverages DP Principal Component Analysis (DP-PCA) to improve learning accuracy. Extensive experimental results demonstrate that DPPrefSyn achieves competitive alignment performance under strong DP guarantees. These findings highlight the potential of synthetic preference data as a practical alternative for privacy-preserving preference alignment across a broad range of applications. To the best of our knowledge, this is the first work to generate DP synthetic preference data for LLM alignment.

Deep Learning · Large Language Models

Chenzhi Hu, Qinzhe Hu, Yuhang Xu, Junyi Chen, Ruijie Wang, Shengzhong Liu, Jianxin Li, Fan Wu, Guihai Chen

Large reasoning models (LRMs) like OpenAI o1 and DeepSeek-R1 achieve high accuracy on complex tasks by adopting long chain-of-thought (CoT) reasoning paths. However, the inherent verbosity of these processes frequently results in redundancy and overthinking. To address this issue, existing works leverage Group Relative Policy Optimization (GRPO) to reduce LRM output length, but their static length reward design cannot dynamically adapt according to the relative problem difficulty and response length distribution, causing over-compression and compromised accuracy. In this paper, we propose *SmartThinker*, a novel GRPO-based efficient reasoning method with progressive CoT length calibration. *SmartThinker* makes a two-fold contribution: First, it dynamically estimates the optimal length with peak accuracy during training, and further guides the overlong responses to approach the optimal length, in order to achieve length reduction while sustaining high accuracy. Second, it dynamically modulates the length reward coefficient to avoid the unwarranted penalization of correct reasoning paths. Extensive experiment results show that *SmartThinker* achieves up to 52.5\% average length compression with improved accuracy, and achieves up to 16.6\% accuracy improvement on challenging benchmarks like AIME25.

Deep Learning · Large Language Models

Yuhang Xu, Kaibin Tian, Yang Tian, Zhice Yang, Yifeng Yu, Yan Li, Shengzhong Liu, Fan Wu, Guihai Chen

Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constitutes a significant efficiency bottleneck, mainly arising from the long-tail bubbles across data parallel ranks, particularly in long-context scenarios where faster GPUs remain idle while waiting for stragglers. Existing solutions, such as partial rollout or asynchronous RL, mitigate these bubbles by compromising the algorithm's strict synchronous nature. Instead, we propose **BubbleSpec**, a novel framework that accelerates RL rollouts while strictly keeping the mathematical exactness. Instead of attempting to eliminate bubbles, BubbleSpec exploits them. We exploit the idle time windows of faster ranks to pre-generate rollout results for subsequent steps, serving as drafts for speculative decoding. Unlike prior speculative methods that rely on historical epoch similarity and warm-ups, BubbleSpec is agnostic to dataset size and provides immediate acceleration from the onset of training. Extensive evaluations demonstrate that BubbleSpec reduces decoding steps by **$\sim$50\%** and increases rollout throughput by up to **1.8$\times$**. Critically, BubbleSpec is seamlessly compatible with various RL frameworks and strategies as it sustains the strict synchronous property of RL algorithms.

Social Aspects · Alignment

Kaizhao Liu, Qi Long, Zhekun Shi, Weijie Su, Jiancong Xiao

Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In this paper, we seek to uncover fundamental statistical limits concerning aligning LLMs with human preferences, with a focus on the probabilistic representation of human preferences and the preservation of diverse preferences in aligned LLMs. We first show that human preferences can be represented by a reward model if and only if the preference among LLM-generated responses is free of any Condorcet cycle. Moreover, we prove that Condorcet cycles exist with probability converging to one exponentially fast under a general probabilistic preference model called the Luce model, thereby demonstrating the impossibility of fully aligning human preferences using reward-based approaches such as reinforcement learning from human feedback. Next, we explore the conditions under which LLMs would employ mixed strategies -- meaning they do not collapse to a single response -- when aligned in the limit using a non-reward-based approach, such as Nash learning from human feedback. We identify a necessary and sufficient condition for mixed strategies: the absence of a response that is preferred over all others by a majority. As a blessing, we prove that this condition holds with high probability under the Luce model, thereby highlighting the statistical possibility of preserving minority preferences without explicit regularization in aligning LLMs.

Social Aspects · Accountability, Transparency, and Interpretability

Gengrui (Edward) Zhang

GenAI systems, particularly LLMs, rely heavily on vast amounts of publicly available digital content as training data. A significant portion of this content is protected by copyright. While large-scale data scraping may be lawful under certain jurisdictions, the use of copyrighted works to generate outputs that compete with or replicate original creations raises unresolved legal, economic, and ethical concerns. In this position paper, we argue that data providers should be fairly compensated based on their measurable contribution to inference-time outcomes, rather than through coarse, one-time licensing or blanket agreements. We examine alternative perspectives on data ownership, fair use, and model training, and discuss why existing approaches fail to align incentives between GenAI developers and content creators. We then outline concrete roadmaps for developing decentralized systems that enable contribution-aware revenue sharing, including mechanisms for attribution, accounting, and payout at scale. We argue that fair revenue distribution for data providers will not only help resolve ongoing legal disputes surrounding GenAI systems, but also foster a new era of collaboration, rather than competition, between model developers and data creators. By incentivizing the production and sharing of high-quality datasets, such mechanisms can ultimately accelerate the development of more robust, trustworthy, and socially sustainable GenAI systems.