论文检索

Social Aspects · Privacy

Zheng Liu, Chen GONG, Terry Yue Zhuo, Zhou Yang, Kecen Li, Wenlong Meng, Xinwen Hou, Yu Liu, Xiaochen Li

Large language models fine-tuned on instruction–code pairs may memorize and subsequently leak sensitive training data. Existing differentially private (DP) code generation methods primarily protect code snippets while assuming prompts are public, which fails in realistic scenarios where prompts may also contain sensitive information. When prompts cannot be explicitly learned or used during generation, code synthesis suffers from severe utility degradation and reduced diversity. To address these challenges, we propose PrivCode++, the first work to explore DP code generation under where both prompts and code snippets are considered sensitive in LLM fine-tuning. PrivCode++ introduces a two-stage DP framework with a Privacy-Free Latent Conditioning module, enabling effective DP fine-tuning and data synthesis without direct access to sensitive prompts or code. Extensive experiments show that PrivCode++ achieves substantially higher utility than baselines, remains competitive with the method with relaxing privacy assumptions, and provides stronger privacy guarantees.

Social Aspects · Alignment

Zidi Xiong, Shan Chen, Himabindu Lakkaraju

As Large Reasoning Models (LRMs) are increasingly deployed, auditing their chain-of-thought (CoT) traces for safety becomes critical. Recent work has reported that monitorability—the degree to which CoT faithfully and informatively reflects internal computation—can appear as a "free gift" during the early stages of Reinforcement Learning with Verifiable Rewards (RLVR). We make this observation concrete through a systematic evaluation across model families and training domains. Our results show that this effect is not universal: monitorability improvements are strongly data-dependent. In particular, we demonstrate the critical role of data diversity and instruction-following data during RLVR training. We further show that monitorability is orthogonal to capability—improvements in reasoning performance do not imply increased transparency. Through mechanistic analysis, we attribute monitorability gains primarily to response distribution sharpening (entropy reduction) and increased attention to the prompt, rather than stronger causal reliance on reasoning traces. We also reveal how monitorability dynamics vary with controlled training and evaluation difficulty. Together, these findings provide a holistic view of how monitorability emerges under RLVR, clarifying when gains are likely to occur and when they are not.

Social Aspects · Fairness

Minh Phu Vuong, Jinyoung Lee, Young-Ju Lee, Chul-Ho Lee

Fair graph clustering has emerged as a critical research area for addressing algorithmic bias in machine learning. The objective is to ensure that the proportion of each protected group within a cluster is consistent with its representation in the entire dataset. However, most existing spectral solutions rely on computationally expensive eigendecompositions of the graph Laplacian, limiting their scalability. In this paper, we propose Riemannian Fair Spectral Clustering (R-FairSC), a novel method that formulates fair spectral clustering as a constrained optimization problem on a Riemannian manifold. We develop a Riemannian alternating direction method of multipliers employing a variable-splitting strategy to efficiently solve the associated subproblems. Numerical experiments on large synthetic and real-world graphs demonstrate that R-FairSC significantly improves computational efficiency over state-of-the-art methods while maintaining high clustering quality and fairness.

Social Aspects · Robustness

Yujie Huang, Wenwu He, Zhuo-Xu Cui

Chain-of-Thought (CoT) prompting enables multi-step reasoning in large language models, yet long-horizon generation remains brittle under distribution shift and context interference: irrelevant cues persist, small deviations compound into inference drift, and late-stage corrections can destabilize the trajectory. We recast autoregressive decoding as a perturbed long-horizon dynamical system and introduce an *inference-time stabilization operator* that targets *trajectory-level* reliability rather than token-level fluency. Specifically, we propose *ODE-guided language models*, which augment a base Transformer with a persistent continuous-time *thought state* whose dynamics are explicitly designed to be dissipative, enabling stable evidence accumulation with controlled forgetting. Instantiating this framework, *Thinking in Flow* (TiF) equips the model with a lightweight Neural ODE controller and injects its output through post-norm residual updates to achieve numerically stable, low-intrusion steering. A demand--supply (uncertainty--capacity) gate determines *when* intervention is warranted, while a direction gate determines *how* to steer in representation space, yielding selective, do-no-harm corrections instead of persistent bias. We establish well-posedness, dissipativity, and incremental stability of the controlled thought dynamics, implying bounded interventions over arbitrarily long contexts, and empirically demonstrate improved robustness to distractions and semantic perturbations, while matching or improving accuracy on mathematical reasoning benchmarks across both the Llama and Qwen model families; we further observe gains on non-mathematical BBH reasoning tasks when training TiF on Llama.

Social Aspects · Alignment

Yang Zhang, Xiukun Wei, Xueru Zhang

Foundation models are increasingly trained on synthetic data generated by prior model iterations rather than exclusively on real data. This *self-consuming* training paradigm can lead to model collapse, divergence, or bias amplification. Recent work (Ferbach et al., 2024) shows that incorporating human curation into the loop can steer a self-consuming model toward human-aligned behavior, but these analyses focus on a single, isolated model that solely consumes its own outputs. In practice, however, models often interact and train on input output pairs produced by other models. This paper studies self-consuming training in the *multi-model* regime. We first formalize a framework for interacting self-consuming models and characterize when the resulting dynamical system converges to a stable point. We then examine how human curation of one model affects its own alignment (self-influence) and how such effects propagate to other models (cross-influence). Unlike isolated settings where human curation always enhances model alignment, we show that cross-model interactions can dampen or even invert this effect, ultimately degrading long-term alignment.

Social Aspects · Safety

Jialin Wu, Wei Shi, Han Shen, Peigui Qi, Kunsheng Tang, Zhicong Huang, Binghao Wang, Zhou Yang

Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textual representations often become intertwined in the deeper network layers. To address this, we propose REVIS, a training-free framework designed to explicitly re-activate this suppressed visual information. Rooted in latent space geometry, REVIS extracts the pure visual information vector via orthogonal projection and employs a calibrated strategy to perform sparse intervention only at the precise depth where suppression occurs. This surgical approach effectively restores visual information with minimal computational cost. Empirical evaluations on standard benchmarks demonstrate that REVIS reduces object hallucination rates by approximately 19% compared to state-of-the-art baselines, while preserving general reasoning capabilities.

Social Aspects · Safety

Qizhuo Han, Xiangrui Cai, Sihan Xu, Ying Zhang, Zheli Liu

While deep neural network-based long-term time series forecasting (LTSF) has become indispensable for critical infrastructures such as smart grids and IoT platforms, the deployment of these models as black-box APIs introduces severe security vulnerabilities that remain largely underexplored. In this paper, we propose TSFAdv, a query-efficient adversarial framework for LTSF models. The framework systematically analyzes model sensitivity to spectral perturbations in both magnitude and phase of the frequency domain. By embedding frequency-domain priors into Natural Evolution Strategies, we achieve sensitivity-guided gradient estimation that improves perturbation efficacy without violating practical query constraints. To overcome ambiguities inherent to point-wise regression metrics, we adopt a trajectory-level evaluation protocol based on Dynamic Time Warping (DTW) and Slope Misalignment Error (SME), enabling the capture of complex geometric and directional deviations. Extensive experiments across seven state-of-the-art architectures demonstrate that TSFAdv achieves substantial performance gains, with average DTW improvements of 21.91–85.00% and SME improvements of 15.04–61.97% under a restrictive 200-query budget. These findings reveal that existing defense mechanisms are ineffective against frequency-domain manipulation, underscoring an urgent necessity for robust LTSF models; the code and artifacts are available at https:// anonymous.4open.science/r/TSFAdv.

Social Aspects · Alignment

Yangneng Chen, Jing Li

Large Vision-Language Models (LVLMs) extend large language models with visual understanding, but remain vulnerable to hallucination, where outputs are fluent yet inconsistent with images. Recent studies link this issue to language bias—the tendency of LVLMs to over-rely on text while neglecting visual inputs. Yet most analyses remain empirical without uncovering its underlying cause. In this paper, we provide a systematic study of language bias and identify its root in modality misalignment during training. Our analysis shows that both Visual Instruction Tuning (VIT) and Direct Preference Optimization (DPO) often prioritize textual improvements, which may cause LVLMs to overly lean toward language modeling rather than balanced multimodal understanding. To address this, we propose two simple yet effective methods: Language Bias Regularization (LBR), which mitigates language bias through regularization during instruction tuning, and Language Bias Penalty (LBP), which penalizes language bias in the DPO training process. Extensive experiments across diverse models and benchmarks demonstrate the effectiveness of our approach. LBR consistently improves performance on over ten general benchmarks, while LBP significantly reduces hallucination and improves trustworthiness. Together, these methods not only mitigate language bias but also advance the overall alignment of LVLMs, all without introducing any additional data or auxiliary models.

Social Aspects · Alignment

Keshav Shenoy, Li Yang, Abhay Sheshadri, Jack Lindsey, Samuel Marks, Rowan Wang

Can we train LLMs to *introspect*, i.e. to faithfully describe their own behaviors in natural language? Prior work has shown some, limited, success. However, it is difficult to scale introspection training due to a lack of ground-truth labels. In this work, we study an approach to introspection training which side-steps this data bottleneck. Given a target model $M$, our method works by fine-tuning models $M_i$ from $M$ with implanted behaviors $b_i$ (such as downplaying medical problems); the $(M_i, b_i)$ pairs serve as labeled introspection training data. We then train an *introspection adapter* (IA): a LoRA adapter jointly optimized across the fine-tunes $M_i$ which causes them to verbalize their implanted behaviors. This IA induces faithful introspection in fine-tunes of $M$ that were trained in very different ways from the $M_i$, as well as in $M$ itself. This is surprising because the IA was never trained on $M$. To demonstrate the utility of IAs, we use them to successfully audit misaligned models introduced in prior work. IAs can also be used to detect fine-tuning API attacks which train models to comply with encrypted harmful requests. Notably, IAs are more effective when applied to larger models. Overall, our results suggest that IAs are a scalable, effective, and practically useful approach to LLM introspection training.

Social Aspects · Security

Pragati Meshram, Varun Chandrasekaran

Effective removal of semantic watermarks requires balancing three competing objectives: \emph{high removal success}, \emph{low perceptual distortion}, and \emph{low computational cost}. However, existing single-image attacks typically optimize only for the first two, achieving strong watermark suppression but relying on expensive, multi-step optimization that limits practical deployment. In this work, we show that this trade-off is fundamental: no current approach achieves all three properties simultaneously. We introduce \textsc{DAWN}, a lightweight, training-free attack that explicitly targets the low-cost regime while maintaining competitive removal performance. \textsc{DAWN} works by projecting a watermarked image onto natural-image priors in complementary frequency and semantic spaces, suppressing watermark signals that deviate from natural statistics, and then applying a decoupled perceptual-alignment step to restore visual consistency with minimal artifact. Across diverse pixel-, frequency-, and latent-space watermarking schemes, \textsc{DAWN} consistently reduces detectability while preserving structural and semantic fidelity, demonstrating that efficient, low-resource watermark removal is feasible with only modest perceptual degradation. Our code is available at \url{https://anonymous.4open.science/r/DAWN-567A/}.

Social Aspects · Safety

Atmadeep Ghoshal, Anasmita Ghoshal, Volodymyr Shevchenko, Ashwini B, Arshia Dutta, Ruba Abu-Salma, Martim Brandao

AI companions function differently from earlier interactive technologies by establishing sustained relational environments through anthropomorphism and continuous validation. This position paper argues that \textbf{Responsible AI for AI companions must actively combat violence toward intimate partners} who may never directly engage with these systems but may experience the consequences of behaviorally conditioned users. We examine how these systems create conditions where users rehearse violent without encountering resistance and we identify structural gaps in existing safety approaches that focus exclusively on direct user protection. Drawing on research on intimate partner violence (IPV), coercive control, and technology-facilitated abuse, we propose three intervention pathways: involving IPV survivors in red-teaming and benchmark development; implementing behavioral monitoring with graduated enforcement mechanisms; and reorienting AI safety research toward granular harm taxonomies capable of detecting longitudinal patterns of violence across extended interactions. Together, these recommendations center non-user security alongside user well-being

Social Aspects · Accountability, Transparency, and Interpretability

Hengyu Liu, TIANYI LI, Zhihong Cui, Yushuai Li, Zhangkai Wu, Torben Pedersen, Kristian Torp, Christian S Jensen

This position paper argues that reliable AI requires infrastructure for human validation of implicit knowledge. AI learns from both explicit knowledge (papers, documentation, structured databases) and implicit knowledge (reasoning patterns, debugging processes, intermediate steps). Implicit knowledge remains unexternalized because documentation cost exceeds perceived value—yet AI learns from it indiscriminately, acquiring both beneficial patterns and harmful biases. Current reliability methods can only verify explicit knowledge against sources, creating a fundamental gap: the most valuable AI capabilities (reasoning, judgment, intuition) are precisely those we cannot verify. We propose Knowledge Objects (KOs)—structured artifacts that externalize implicit knowledge into forms humans can inspect, verify, and endorse. KOs transform verification economics: what was previously too costly to verify becomes feasible, enabling accumulated human validation to improve reliability over time.

Social Aspects · Accountability, Transparency, and Interpretability

Giovanni De Felice, Riccardo D`Elia, Alberto Termine, Pietro Barbiero, Giuseppe Marra, Silvia Santini

Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal model computations, without addressing whether they align or not with how a human would reason about the studied phenomenon. Instead, we state interpretability in deep time series models should pursue semantic alignment: predictions should be expressed in terms of variables that are meaningful to the end user, mediated by spatial and temporal mechanisms that admit user-dependent constraints. In this paper, we formalize this requirement and require that, once established, semantic alignment must be preserved under temporal evolution: a constraint with no analog in static settings. Provided with this definition, we outline a blueprint for semantically aligned deep time series models, identify properties that support trust, and discuss implications for model design.

Social Aspects · Safety

Arthur Goemans, Daniel Altman, Noemi Dreksler, Jonas Freund, Milan Gandhi, Zhengdong Wang, Sarah Cogan, Sebastien Krier, Demetra Brady, Lewis Ho 等

Frontier AI governance often centres on the model-level governance paradigm, which assumes that a model’s capability profile is primarily a function of the compute and data used during training. This position paper argues that model-level governance becomes less effective when capability progress is increasingly driven by "non-model gains"—improvements that are independent from advances in the base model. We formalise the concept of non-model gains and provide a taxonomy of three distinct vectors of capability gain: inference gain (scaling compute at test-time), systems gain (post-training enhancements such as scaffolds), and asset gain (enhancing a model with restricted assets). We demonstrate how these vectors—alongside potential future impacts from embodiment, continual learning, and diffusion—may undermine risk management strategies that hinge mostly on pre-deployment evaluation and mitigation. We provide an overview of governance approaches that go beyond the model level: system, entity, agent, and cloud governance. Finally, we emphasise the importance of societal resilience as a complement to these governance layers.

Social Aspects · Accountability, Transparency, and Interpretability

Yazheng Liu, Xi Zhang, Sihong Xie, Hui Xiong

Temporal graphs are ubiquitous in real-world applications such as social networks and finance, where Temporal Graph Networks (TGNs) capture both structural and temporal dependencies, achieving in superior predictive accuracy. Understanding which historical events drive specific model predictions can enhance trustworthiness of TGNs. Existing explanation methods overlook the memory module, the core component that records and updates node histories, leaving the influence of past events unexplored. To address this challenge, we propose a method that attributes TGNs predictions through the topology attribution tree and memory backtracking tree. The topology attribution tree captures the influence of neighbors and their memory vectors, then the memory backtracking tree quantifies how historical events shape node memory vectors. We apply the LRP in TGNs, ensuring that the total contribution of events equals the model’s logits. Finally, top-k selection may lack faithfulness due to the nonliear relationship between logits and probabilities. We design optimization objectives to map logits to probabilities and identify the important events. Experiments on nine temporal graph datasets, spanning node property prediction, link prediction tasks and graph classification tasks, show that our method provides faithful explanations and outperforms state-of-the-art baselines.

Social Aspects · Everything Else

Pedram Bakhtiarifard, Pınar Tözün, Christian Igel, Raghavendra Selvan

Sustainability encompasses three key facets: economic, environmental, and social. However, the nascent discourse that is emerging on sustainable artificial intelligence (AI) has predominantly focused on the environmental sustainability of AI, often neglecting the economic and social aspects. Achieving truly sustainable AI necessitates addressing the tension between its climate awareness, which emphasizes the need to mitigate AI's environmental impacts, and its social sustainability, which hinges on equitable access to AI development resources. The concept of resource awareness advocates for AI sovereignty through broader access to the infrastructure required to develop AI. Yet, this push for improving accessibility often overlooks the environmental costs of expanding such resource usage. This position paper argues that reconciling climate awareness and resource awareness is essential to realizing sustainable AI and neglecting these factors fuelling the global AI arms race. By applying the base-superstructure framework from historical materialism, we analyze how the material conditions are shaping the current AI progress and the discourse surrounding it. We also introduce the Climate and Resource Aware Machine Learning (CARAML) framework to address the conflict between climate and resource awareness of AI, with actionable recommendations spanning individual, community, industry, government, and global levels to achieve sustainable AI.

Social Aspects · Fairness

Samuel Gruffaz, Gabriel Singer, Olivier VO VAN, Nicolas Vayatis, Argyris Kalogeratos

In many machine learning applications acquiring reliable ground-truth labels is costly, or unfeasible, leading practitioners to rely on crowdsourcing and aggregation of noisy human annotations. When labels are subjective, however, aggregation may amplify individual biases, particularly with respect to sensitive attributes, raising fairness concerns. Despite this, fairness in crowdsourced aggregation remains largely unexplored, with no existing convergence guarantees and only limited post-processing approaches for enforcing $\varepsilon$-fairness under demographic parity. We address this gap by analyzing fairness properties of crowdsourcing aggregation methods within the $\varepsilon$-fairness framework, focusing on Majority Voting and Optimal Bayesian aggregation. In the small-crowd regime, we derive an upper bound on the fairness gap of Majority Voting in terms of the individual annotators’ fairness gaps. We further show that the fairness gap of the aggregated consensus converges exponentially fast to that of the ground truth under interpretable conditions. Since the ground truth itself may still be unfair, we generalize a state-of-the-art multiclass fairness post-processing algorithm from the continuous to the discrete setting, enabling the enforcement of strict demographic parity constraints for any aggregation rule. Experiments on both synthetic and real-world datasets demonstrate the effectiveness of our approach and corroborate the theoretical insights.

Social Aspects · Accountability, Transparency, and Interpretability

Ted Fujimoto, Benz

The advancement of AI capabilities compels researchers and the public to be more aware of its potential worldwide impact. A pressing near-term concern is the regulation of military AI applications. Armament manufacturers and defense contractors are increasingly investing in AI capabilities and forging partnerships with AI companies, creating a burgeoning coalition that demands military leaders, arms control diplomacy experts, and AI researchers collaborate to ensure a safer future. While AI researchers often focus on the long-term implications of superintelligent AI, this approach may not adequately address the immediate challenges posed by AI in military applications. Success requires acknowledging and mitigating the emerging risks of frontier AI models that plan to be applied defense applications, like military AI systems. Arms control has reduced past catastrophic risks, so lessons learned from nuclear deterrence can guide AI safety and security research towards innovations in verification and diplomacy. AI researchers, however, must assist in leading the technical research that clearly defines and alleviates instability in military settings. Given these new responsibilities and the lack of sufficiently reliable solutions, we argue that AI researchers must take a leading role in advancing arms control research to minimize risk in military AI applications.

Social Aspects · Privacy

Hilal Asi, Hongjie Chen

We study the problem of private hypothesis selection: given samples from an unknown distribution drawn from a finite hypothesis class, the goal is to identify the best hypothesis under the constraint of differential privacy. Existing algorithms for this problem are either computationally expensive or achieve sub-optimal statistical rates. We propose new algorithms that achieve near-optimal rates while running in nearly linear time in the number of hypotheses. Rather than applying the exponential mechanism directly with a score function that requires pairwise comparisons between hypotheses, our approach introduces a carefully designed loss function based on a small set of strong hypotheses. This structure allows the score to be evaluated efficiently for most hypotheses, yielding significant computational savings. We further extend our algorithms to the agnostic setting, where the true distribution may not belong to the hypothesis class. As an application, we obtain faster differentially private algorithms for universal statistical estimation in low dimensional settings.

Social Aspects · Accountability, Transparency, and Interpretability

Constantin Venhoff, Iván Arcuschin, Phil Torr, Arthur Conmy, Neel Nanda

Why do thinking language models outperform their base counterparts, and what exactly do they learn during training? We introduce constructive model diffing, a framework for understanding fine-tuned models by explicitly constructing the base-to-fine-tuned difference from interpretable components to produce hybrid models, and measuring how well they recover the fine-tuned model's performance. For thinking models, we decompose the diff into two components: reasoning mechanisms (steering vectors that activate specific behaviors in the base model) and reasoning heuristics (a classifier that determines when each mechanism should fire). To ground this decomposition, we develop an unsupervised methodology using Sparse Autoencoders to discover interpretable taxonomies of reasoning behaviors. Evaluating nine model configurations (five RL-trained, four distilled), we find a striking difference between training methods: the hybrid models for the five RL-trained models achieve much higher performance recovery compared to the four distilled models. This indicates RL-trained models primarily learn sophisticated heuristics for deploying pre-existing base model mechanisms, while distillation affects the mechanisms themselves. These results provide a new lens for understanding what different training paradigms teach, with potential implications for efficient reasoning model development.