Papers

Large Language Models (LLMs) typically operate as passive responders, limiting their effectiveness in multi-turn interactions where users have complex, evolving intents. This research introduces COLLAB LLM, a novel training framework that leverages a collaborative simulation to estimate the long-term impact of responses through Multiturn-aware Rewards (MR). By applying reinforcement learning with these rewards, COLLAB LLM encourages active intent discovery and insight- ful suggestions from the model, thereby transforming the nature of user-LLM interactions. We propose a multiturn interaction benchmark that includes three challenging tasks, such as collaborative document creation. Preliminary results indicate that COLLAB LLM outperforms traditional models with an average of 18.5% higher task performance and 46.3% improved interactivity, as rated by LLM judges. Furthermore, a large user study with 201 participants revealed an increase in user satisfaction by 17.6% and a reduction in time spent by 10.4%. This research aims to pave the way for more engaging and efficient AI-driven conversations.

As machine learning becomes integral to government programs aimed at identify- ing and assisting the most vulnerable populations, this paper investigates whether improving predictive accuracy is more beneficial than expanding screening capac- ity. We hypothesize that in typical operational conditions, enhancing capacity to reach more individuals will provide greater benefits than marginal gains in pre- diction accuracy. We introduce the Prediction-Access Ratio (PAR) to quantify this trade-off, guiding policymakers on when to invest in better models versus ex- panding access. Utilizing both mathematical modeling and a case study on long- term unemployment among German jobseekers, we demonstrate that expanding screening capacity generally leads to improved identification of the worst-off. Our findings empower policymakers with actionable insights, enabling more effective allocation of resources in equity-driven contexts.

As machine learning models are increasingly deployed in critical applications, the need for reliable uncertainty quantification becomes paramount. Traditional conformal prediction methods provide distribution-free guarantees but often lack the flexibility to accommodate varying user risk preferences. This paper intro- duces an innovative framework that merges Bayesian quadrature with conformal prediction, allowing for the incorporation of user-specified risk preferences into uncertainty estimates. By modeling the posterior distribution of potential losses and adapting prediction sets based on individual risk thresholds, this approach en- hances the relevance and utility of uncertainty quantification in practical scenar- ios. Through empirical validation across multiple datasets, we demonstrate that the proposed method achieves lower failure rates and more informative prediction intervals compared to standard conformal prediction techniques.

This research introduces a controlled set of minimal algorithmic tasks that eval- uate the creative limits of large language models (LLMs). These tasks require a stochastic planning step that either discovers novel connections in knowledge graphs or constructs new patterns, simulating open-ended real-world challenges. We propose that traditional next-token learning is myopic, whereas multi-token prediction (MTP) approaches, such as teacherless training and diffusion models, excel in producing diverse and original outputs. Our novel seed-conditioning tech- nique, which introduces randomness at the input layer, is presented as an effective method to elicit creativity without sacrificing coherence, performing comparably to existing output-layer temperature sampling. This study aims to provide a prin- cipled framework for assessing the creative capabilities of LLMs and advocates for a shift away from conventional next-token learning paradigms.

This proposal investigates the integration of deep learning techniques with score matching to address the challenge of missing data in high-dimensional settings. Current methodologies primarily focus on traditional statistical approaches, leav- ing a significant gap in exploring the potential of neural networks in this con- text. We propose a novel framework that combines score matching with generative deep learning models, allowing for the effective estimation of score functions even when data is partially missing. Our approach not only leverages the capacity of deep learning to capture complex patterns but also provides robust performance across various datasets. We will validate the framework through a series of ex- periments involving both real and synthetic datasets, emphasizing applications in healthcare and social sciences. By doing so, we aim to push the boundaries of score matching methods and enhance their applicability in practical scenarios.

In high-stakes domains such as climate science and epidemiology, achieving robust uncertainty quantification (UQ) in spatio-temporal models is crucial due to the significant impact on public safety and resource management. Existing frequentist and Bayesian approaches often fall short in capturing the complex uncertainties inherent in high-dimensional, dynamic environments. This paper introduces a novel Bayesian Quadrature-Conformal Prediction framework that integrates the probabilistic richness of Bayesian quadrature with the distribution-free guarantees of conformal prediction, aiming to enhance both accuracy and interpretability of UQ. Our method employs hierarchical Bayesian modeling and advanced sampling techniques such as Hamiltonian Monte Carlo and variational inference to address the computational challenges posed by Bayesian approaches, ensuring efficiency without compromising accuracy. Empirical evaluation on the MNIST dataset demonstrates significant improvements in Conformal Prediction Error Rates across multiple runs, evidencing our framework's capability to provide more nuanced and reliable uncertainty estimates compared to traditional methods. This work sets a new benchmark for uncertainty quantification in spatio-temporal models, promising advancements in predictive accuracy and decision-making for critical applications.

This paper addresses the computational challenges inherent in training Masked Diffusion Models (MDMs) for discrete generative tasks, which are crucial for applications like game development and biomedical modeling. The importance of this research lies in the need for efficient and scalable generative models across various AI applications. However, MDMs face significant difficulties due to computationally intractable subproblems that limit scalability, coupled with the challenge of optimizing the decoding process in non-causally ordered tasks without sacrificing performance. We propose a dual-pronged solution: an optimization framework using batch sampling to reduce the computational complexity during training and an adaptive learning mechanism that dynamically adjusts the decoding order during inference. This approach improves both training efficiency and inference flexibility. Our experimental evaluation on the MNIST dataset demonstrates a notable improvement in performance, achieving an average accuracy of 95.53\% and maintaining an average inference time of 7.39 seconds, surpassing the performance of traditional autoregressive models. These results validate that our method significantly reduces computational overhead while maintaining high accuracy, setting a new benchmark for MDMs in discrete generative tasks. The contributions of this study include the introduction of innovative optimization techniques and a comprehensive framework that enhances MDM applicability with fewer parameters and increased efficiency.

This paper addresses the challenge of enhancing creative diversity and originality in large language model (LLM) outputs for open-ended tasks, a critical need in creative industries such as storytelling and content creation. Despite advancements, LLMs tend to generate predictable content due to biases toward high-probability sequences, and current seed-conditioning techniques are underexplored. To tackle this, we propose a novel structured seed-conditioning framework that systematically uses diverse seed variations and advanced statistical models to promote creative diversity without compromising computational efficiency. Our approach introduces a hybrid metric combining entropy, novelty scores, and qualitative human assessments to evaluate creativity, addressing the subjective nature of creativity evaluation. Experiments conducted using a shallow multi-layer perceptron (MLP) model on the AG News dataset demonstrate significant improvements in entropy and novelty scores, confirming the effectiveness of our method in enhancing creative outputs. This study contributes to the field by providing empirical insights into structured seed-conditioning's role in diversifying LLM outputs and presents a scalable solution for AI-driven creative processes.

Masked diffusion models (MDMs) have emerged as a powerful paradigm for gen- erative modeling over discrete domains. However, their training often involves solving computationally intractable problems, while their inference capabilities remain underutilized. In this work, we propose to enhance the performance of MDMs by introducing adaptive inference strategies that allow for dynamic token ordering during decoding. We demonstrate that by sidestepping computationally heavy subproblems, pretrained MDMs can achieve significant performance im- provements on complex tasks such as logic puzzles. Our experiments show that adaptive inference boosts Sudoku solving accuracy from less than 7% to approx- imately 90%, even outperforming autoregressive models with significantly more parameters. This work opens new avenues for leveraging the strengths of MDMs in discrete generative tasks.

This paper addresses the challenge of enabling large language models (LLMs) to dynamically discover and adapt to user intents during long-term interactions. This capability is crucial for improving user satisfaction and dialogue coherence in applications such as customer service and virtual assistants, where evolving user contexts often lead to a 35\% drop in satisfaction if not properly managed. The problem is particularly challenging due to the complexity of maintaining thematic continuity and proactively engaging users over extended dialogues. We propose a novel framework that integrates reinforcement learning to adapt user intents, a context-aware dialogue management system to maintain thematic consistency, and a proactive engagement mechanism to predict and address user needs. Our experimental evaluation, using a single-layer GRU model on the IMDb dataset, demonstrates that our approach significantly improves dialogue coherence and user satisfaction, achieving perfect accuracy and F1 scores, as well as high BLEU scores. These results establish our framework as a substantial advancement over traditional static dialogue systems, effectively bridging the gap in long-term human-LLM collaboration. Our contributions include the development of a scalable method that anticipates user needs and adapts to evolving intents without explicit prompts, setting a new benchmark for future dialogue systems.

As artificial intelligence, particularly generative AI, continues to reshape labor markets, traditional AI safety frameworks prioritize existential and technical risks while overlooking critical human-centric challenges. This position paper advo- cates for a paradigm shift towards a pro-worker governance framework that ad- dresses the systemic risks posed by AI on economic justice and labor rights. We identify six key risks, including the exacerbation of technical debt, disproportion- ate job displacement, and the monopolistic tendencies of AI firms. By propos- ing actionable interventions such as collective licensing for AI-generated content, mandatory AI watermarking, and robust retraining policies, we aim to enhance the resilience of labor markets. This paper calls for an inclusive dialogue among stakeholders, emphasizing the need for policies that not only safeguard against the adverse effects of AI but also promote shared prosperity. Our framework aims to establish a sustainable relationship between AI and labor that empowers workers and fosters equitable growth.

The rapid increase in submissions to AI conferences has led to a crisis in the peer review process, characterized by declining review quality and accountability. This position paper proposes a novel bi-directional feedback mechanism where authors can evaluate the quality of reviews while safeguarding against retaliation. Cou- pled with a blockchain-enabled reviewer rewards system, this framework aims to incentivize high-quality reviewing and create an accountability structure that ben- efits all stakeholders. By allowing authors to provide feedback on reviews and rewarding reviewers with transparent digital credentials, this system fosters a cul- ture of quality and responsibility in the peer review process. We call upon the AI community to engage in this vital conversation and explore these transformative reforms for sustainable peer review practices.

The rapid increase in submissions to AI conferences has led to a crisis in the peer review process, characterized by declining review quality and accountability. This position paper proposes a novel bi-directional feedback mechanism where authors can evaluate the quality of reviews while safeguarding against retaliation. Cou- pled with a blockchain-enabled reviewer rewards system, this framework aims to incentivize high-quality reviewing and create an accountability structure that ben- efits all stakeholders. By allowing authors to provide feedback on reviews and rewarding reviewers with transparent digital credentials, this system fosters a cul- ture of quality and responsibility in the peer review process. We call upon the AI community to engage in this vital conversation and explore these transformative reforms for sustainable peer review practices.

The paper addresses the critical issue of AI-induced income inequality, focusing on developing an adaptive AI governance model that integrates real-time data analytics and local economic contexts to mitigate labor market disruptions. As AI technologies rapidly transform global labor markets, they pose a significant risk of job displacement and income disparity, necessitating adaptable governance frameworks. The challenge lies in creating a globally applicable model that accurately reflects diverse economic environments, predicts AI's long-term impacts, and balances innovation with worker protection. Our proposed solution is a sophisticated predictive analytics platform employing machine learning, Monte Carlo simulations, and agent-based modeling to simulate AI adoption scenarios and their effects on labor markets. Experiments utilizing a shallow MLP architecture on the \texttt{ag\_news} dataset demonstrate consistent prediction accuracy, with Mean Absolute Error (MAE) values ranging from 0.2518 to 0.2849, although R-squared scores were negative, indicating limitations in data representation. The main contributions of this study include a novel governance model that anticipates and mitigates AI's socio-economic impacts, offering dynamic policy recommendations tailored to local conditions. This research provides a foundation for future work on enhancing model accuracy and applicability by incorporating more comprehensive datasets and complex architectures.

AAdaptive token-ordering strategies for masked diffusion models (MDMs) and autoregressive models (ARMs) are critical for addressing the inherent imbalance in subproblem difficulties during sequence generation, which becomes increasingly relevant as models scale to complex reasoning tasks. In this work, we tackle the challenge of dynamically adjusting the token generation order via a reinforce- ment learning framework that optimizes the cumulative predictive V-information,formally defined as I_V (X → Y ) = HV (Y |∅) − HV (Y |X), to preferentially solve easier subproblems first. Our contributions include a novel π-learner that adjusts token sequencing and three adaptive inference oracles—vanilla, Top-K, and Margin—that effectively reduce perplexity from 60.0 to 52.0 while preserving token diversity (entropy shifting from 4.8 to 4.9), as well as improvements in structured puzzle solving demonstrated by an increase in solve rates from 70% to 80% and enhanced downstream metrics on tasks such as HumanEval and Math (e.g., pass@1 scores improving from 60% to 66%). Experimental validation spans scaling law analyses, where validation NLL drops from approximately +3.0 at 109 FLOPs to −5.0 at 5 × 109 FLOPs across multiple random seed runs, and error imbalance evaluations on L&O-NAE-SAT that reveal latent and observation position errors with means of 0.7976 and 0.9724, respectively. Collectively, these results confirm that adaptive token ordering not only mitigates computational intractability in hard token predictions but also enhances both likelihood-based metrics and generalization performance over fixed ordering strategies.

Adaptive prompt-enhanced score matching for partially observed data addresses the challenging problem of recovering score functions from datasets with significant missing entries, where traditional imputation methods or naı̈ve score estimators often fail to achieve reliable parameter recovery and structural inference. In our work, we consider both marginal Importance-Weighted (Marg-IW) and marginal Variational (Marg-Var) approaches to estimate the score function, using a surrogate mean squared error loss. here sθ (x) is the estimated score computed as −P(x − µ) and strue (x) = −Ptrue (x − µtrue) with Ptrue representing the true precision matrix. This formulation inherently accounts for the missingness mechanism, typically modeled as MCAR with a missing rate of 30%, and is further stabilized via techniques such as log-sum-exp and gradient clipping. Our contributions include the integration of a meta-learning prompt generator, which dynamically selects key hyperparameters (e.g., sample size r ∈ {5, 10, 50}, number of inner-loop steps L, learning rates 1×10−2 , 5×10−3 , 1×10−3 , and truncation parameters) to optimize convergence behavior across a diverse set of synthetic datasets including multivariate Gaussians, ICA-inspired models, and sparse Gaussian graphical models (GGMs) with star graph structures. Experimental results demonstrate significant improvements: for instance, in the Gaussian experiment the loss reduced from 9.687 at iteration 50 to 0.094 at iteration 300 and the corresponding parameter error decreased from 3.033 to approximately 2.030, while in the GGM case, the ROC AUC improved from 0.219 to 0.97, thereby confirming our method’s efficacy in both parameter estimation and structure recovery under partial observations. These empirical validations underscore the relevance of adaptive score matching in high-dimensional and complex data regimes, set against the inherent difficulties of handling missing data and ensuring numerical stability in the estimation process, and pave the way for future extensions to accommodate MNAR scenarios and diffusion-based denoising score matching frameworks.

Our work addresses the challenge of optimizing long-term multiturn human–LLM collaboration by introducing an ensemble of Monte Carlo-based reward predictors, Bayesian meta-calibration, and an uncertainty-guided clarification module that dynamically triggers clarifying interactions; in particular, we estimate the conversation-level reward as R∗ (t|g) = Rext (t, g) + Rint (t), where Rext (t, g) quantifies task-specific success (e.g. BLEU scores reaching up to 80% in document editing and unit test pass rates near 70% in code generation) and Rint (t) incorporates an efficiency penalty defined as − min[λ · TokenCount(t), 1] with λ = 0.01, augmented by an LLM-based interactivity score; our approach further employs Bayesian linear regression to aggregate the ensemble signals into a unified reward while simultaneously providing an uncertainty metric which, if exceeding a predefined threshold (e.g., 0.15), triggers an auxiliary clarification round that improves the aggregated outcome—this mechanism is mathematically formulated and empirically validated through improvements such as an increase in accuracy from 73.9% to 79.9% in mathematical problem solving and a resolution of ambiguous dialogue from 80% to 100% as reflected in our experiments; challenges arise due to noisy reward estimations and the trade-off between immediate task performance and long-term conversational quality, which we address via extensive ablation studies on window sizes (with w ∈ {1, 2, 3}) and Monte Carlo sample counts (e.g. S ∈ {3, 5}), as summarized in Table 1 (e.g., MediumDocEdit-Chat: BLEU 0.625 → 0.637, BigCodeBench-Chat: Unit Test Pass Rate 0.532 → 0.489, MATH-Chat: Accuracy 0.739 → 0.799, Abg-CoQA: Macro Accuracy/F1 0.8 → 1.0); overall, this work contributes a robust framework that integrates ensemble learning, uncertainty estimation, and dynamic clarification to effectively enhance the collaborative potential between human users and language models in complex, multi-turn settings.

This work presents a comprehensive framework for quantifying the trade-off between prediction accuracy and screening access in policy evaluation, where we address the challenge of identifying and targeting the worst-off individuals through the rigorous estimation of a policy value function defined as V (α, β, R2 ) = √ Φ2 (zα ,zβ ;ρ)/β, with zα = Φ−1 (α), zβ = Φ−1 (β), and ρ = R2 ; our approach introduces the Prediction-Access Ratio (PAR) as a metric to quantify the rela tive impact of finite improvements in screening thresholds versus enhancements in predictive accuracy, thereby overcoming challenges associated with non-linear sensitivities such as ∂V/∂α ≈ 1.77513 AND ∂V/∂R2 ≈ 0.61282. We verify our framework using extensive simulation experiments on synthetic datasets in which a complex model’s Test R2 improves from 0.16866 to 0.32661 through residual scaling with δ = 0.1 and an associated empirical policy value V (α, β) increases from 0.70000 to 0.80000; and are further supported by capacity gap analyses which demonstrate that a minimal additional screening increment, ∆α∗ ≈ 0.0300, can yield gains comparable to those from complex model enhancements; this integrated strategy thereby provides actionable insights for policy interventions aimed at equalizing access while maintaining efficiency, a pertinent issue given the inherent difficulties arising from the interplay between prediction improvement and screening capacity in heterogeneous populations.

Algorithmic creativity in text generation poses significant challenges in balancing coherence, diversity, and memorization, and our study addresses these challenges by systematically comparing traditional next-token prediction (NTP) with multi-token teacherless prediction (MTP) and discrete diffusion methods (SEDD) across minimal yet representative combinatorial tasks such as Sibling Discovery, Triangle Discovery, Circle Construction, and Line Construction; our primary objective is to maximize the creative output defined as the fraction of generated samples that satisfy task-specific outputs validity criteria, which we quantify as ĉr = #coherent/#total outputs, and to minimize memorization, observed to drop from 100% under deterministic conditions to near 0% when employing controlled stochastic, while diversity is measured by D = |{unique-outputs}|total outputs with values reaching up to 1.00 in optimized settings; to achieve these ends, we introduce seed-conditioning and temperature scaling—modeled by the parameter T where T = 0 corresponds to greedy decoding and T > 0 introduces controlled noise following the relation pnoise = min(0.9, α × T ) with α varying by method—to guide the output generation process, and we formulate an alignment loss to ensure semantic consistency between the restrictive and adaptive prompts; extensive experimentation and rigorous ablation studies, as summarized in Table 1 (detailing coherence rates between 50% and 80%, memorization rates dropping from 100% to nearly 0%, and diversity metrics peaking at 1.00), validate that both MTP and SEDD outperform NTP under non-deterministic settings and when augmented with seed-conditioning, thereby demonstrating that our hybrid framework not only pushes the boundaries of algorithmic creativity on minimal open-ended tasks but also offers a scalable approach for more complex problem domains.

In this work, we propose a scalable framework to simulate the labor market impacts of the ChatGPT event using a two-stage dynamic prompt tuning mechanism combined with an LLM-based qualitative classifier; our objective is to operationalize labor displacement signals (P1) alongside shared prosperity (P3) and detectability (P6) by addressing the inherent challenges of dynamic prompt adaptation and qualitative taxonomy mapping. We tackle the complexity of evolving labor market signals through gradient-based meta-learning updates, modeled as ∆s = αst−1 + ϵ, and employ a Difference-in-Differences regression of the form Yit = β0 + β1 Treatmentit + γi + δt + εit to quantify the impact on employment metrics, notably obtaining a significant negative treatment coefficient of approximately −5.71 (with p < 0.001). Our qualitative classifier achieves a robust accuracy of 74.97% in mapping job narratives to six predefined propositions, and supplemental analyses—such as a principal component analysis (PCA) yielding an AI Capacity Index and its near-zero correlation (r ≈ 0.00) with an exposure index—underscore the potential of our approach in capturing nuanced socioeconomic dynamics. Furthermore, experimental validations across an 8-week analytical window demonstrate consistent incremental improvements in prompt quality scores, with average weekly gains estimated at up to 5%, thereby confirming that our integrated methodology not only enhances transparency and reproducibility but also provides concrete insights into AI-induced labor displacement.