论文检索

Social Aspects · Trustworthy Machine Learning

Senrong Xu, Yanke Zhou, Yuhao Tan, Zenan Li, Yuan Yao, Taolue Chen, Feng Xu, Xiaoxing Ma

Conformal prediction methods provide statistically rigorous marginal coverage guarantees for machine learning models, but such guarantees fail to account for algorithmic biases, thereby undermining fairness and trust. This paper introduces a fair conformal inference framework for classification tasks. The proposed method constructs prediction sets that guarantee conditional coverage on adaptively identified subgroups, which can be implicitly defined through nonlinear feature combinations. By balancing effectiveness and efficiency in producing compact, informative prediction sets and ensuring adaptive equalized coverage across unfairly treated subgroups, our approach paves a practical pathway toward trustworthy machine learning. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of the framework.

Applications · Physics

Dmitry Bylinkin, Mikhail Aleksandrov, Savelii Chezhegov, Aleksandr Beznosikov

Physics-informed neural networks (PINNs) have gained prominence in recent years and are now effectively used in a number of applications. However, their performance remains unstable due to the complex landscape of the loss function. To address this issue, we reformulate PINN training as a nonconvex-strongly concave saddle-point problem. After establishing the theoretical foundation for this approach, we conduct an extensive experimental study, evaluating its effectiveness across various tasks and architectures. Our results demonstrate that the proposed method outperforms the current state-of-the-art techniques.

General Machine Learning · Transfer, Multitask and Meta-learning

Jianheng Tang, Yajiang Huang, Kejia Fan, Feijiang Han, Jiaxu Li, Jinfeng Xu, Run He, Anfeng Liu, Houbing Song, Huiping Zhuang 等

Federated Learning (FL) is a popular distributed learning paradigm to break down data silo. Traditional FL approaches largely rely on gradient-based updates, facing significant issues about heterogeneity, scalability, convergence, and overhead, etc. Recently, some analytic-learning-based work has attempted to handle these issues by eliminating gradient-based updates via analytical (i.e., closed-form) solutions. Despite achieving superior invariance to data heterogeneity, these approaches are fundamentally limited by their single-layer linear model with a frozen pre-trained backbone. As a result, they can only achieve suboptimal performance due to their lack of representation learning capabilities. In this paper, to enable representable analytic models while preserving the ideal invariance to data heterogeneity for FL, we propose our Deep Analytic Federated Learning approach, named DeepAFL. Drawing inspiration from the great success of ResNet in gradient-based learning, we design gradient-free residual blocks in our DeepAFL with analytical solutions. We introduce an efficient layer-wise protocol for training our deep analytic models layer by layer in FL through least squares. Both theoretical analyses and empirical evaluations validate our DeepAFL's superior performance with its dual advantages in heterogeneity invariance and representation learning, outperforming state-of-the-art baselines by up to 5.68%-8.42% across three benchmark datasets. Related code is available at https://github.com/tangent-heng/DeepAFL.

Deep Learning · Everything Else

Md Zesun Ahmed Mia, Malyaban Bal, Abhronil Sengupta

The quadratic complexity of self-attention mechanism presents a significant impediment to applying Transformer models to long sequences. This work explores computational principles derived from astrocytes—glial cells critical for biological memory and synaptic modulation—as a complementary approach to conventional architectural modifications for efficient self-attention. We introduce the Recurrent Memory Augmented Astromorphic Transformer (RMAAT), an architecture integrating abstracted astrocyte functionalities. RMAAT employs a recurrent, segment-based processing strategy where persistent memory tokens propagate contextual information. An adaptive compression mechanism, governed by a novel retention factor derived from simulated astrocyte long-term plasticity (LTP), modulates these tokens. Attention within segments utilizes an efficient, linear-complexity mechanism inspired by astrocyte short-term plasticity (STP). Training is performed using Astrocytic Memory Replay Backpropagation (AMRB), a novel algorithm designed for memory efficiency in recurrent networks. Evaluations on the Long Range Arena (LRA) benchmark demonstrate RMAAT's competitive accuracy and substantial improvements in computational and memory efficiency, indicating the potential of incorporating astrocyte-inspired dynamics into scalable sequence models.

Reinforcement Learning · Deep RL

Claas Voelcker, Axel Brunnbauer, Marcel Hussing, Michal Nauman, Pieter Abbeel, Radu Grosu, ERIC EATON, Amir-massoud Farahmand, Igor Gilitschenski

Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines training stability. Improving a policy through state-action value functions, for example by differentiating Q with regard to the policy, alleviates the variance issues. However, this requires an accurate action-conditioned value function, which is notoriously hard to learn without relying on replay buffers for reusing past off-policy data. We present Relative Entropy Pathwise Policy Optimization, an algorithm that trains Q-value models purely from on-policy trajectories, unlocking the use of Q function derivatives to compute policy updates in the context of on-policy learning. We show how to combine stochastic policies for exploration with constrained updates for stable training, and evaluate important architectural components that stabilize value function learning. This results in an efficient on-policy algorithm that combines the stability of Q-based policy gradients with the simplicity and minimal memory footprint of standard on-policy learning. Compared to state-of-the-art on two standard GPU-parallelized benchmarks, REPPO provides strong empirical performance at superior sample efficiency, wall-clock time, memory footprint, and hyperparameter robustness.

Deep Learning · Attention Mechanisms

Feijiang Han, Xiaodong Yu, Jianheng Tang, Delip Rao, Weihua Du, Lyle Ungar

Token-level attention tuning -- a class of training-free methods including Post-hoc Attention Steering (PASTA) and Attention Calibration (ACT) -- has emerged as a promising approach for improving frozen LLMs via interpretable interventions. However, these methods rely on auxiliary heuristics to identify important task-specific tokens, which can introduce bias and limit applicability when token importance is ambiguous or when optimized kernels make attention maps inaccessible. We propose a simpler alternative: intervening only on the initial token (e.g., in LLaMA). We theoretically show that adding lightweight biases to this token’s attention logits systematically shifts and reshapes downstream attention patterns -- an effect amplified by its natural role as an attention sink. Empirically, we find that this tuning can improve LLM performance and better elicit pretrained knowledge, with stronger effects in early layers and distinct scaling preferences across attention heads. Building on these findings, we introduce ZeroTuning, a training-free method that improves LLM performance by applying head-specific attention adjustments to the initial token, requiring no parameter updates. We present two variants: a supervised mode that calibrates on validation examples, and an unsupervised mode that directly minimizes output entropy. ZeroTuning requires no KV-cache or decoding changes and is kernel-agnostic (works with SDPA and FlashAttention). It requires only four lines of modification to standard \texttt{LlamaAttention} code, achieves gains across 15 datasets, and outperforms prior, more complex methods. For example, on Llama-3.1-8B, it yields relative improvements of 19.9% on classification, 4.5% on question answering, and 2.1% on dialogue. ZeroTuning also works out of the box with quantized inference and maintains its improvements as context length increases. Our work provides a lightweight tool for inference-time improvement, advancing both optimization and interpretability. Our code and runnable demo are available at https://anonymous.4open.science/r/ZeroTuning.

Deep Learning · Everything Else

Akshit Sinha, Arvindh Arun, Shashwat Goel, Steffen Staab, Jonas Geiping

Does continued scaling of large language models (LLMs) yield diminishing returns? In this work, we show that short-task benchmarks may give an illusion of slowing progress, as even marginal gains in single-step accuracy can compound into exponential improvements in the length of tasks a model can successfully complete. Then, we argue that failures of LLMs when simple tasks are made longer arise from mistakes in execution, rather than an inability to reason. So, we propose isolating execution capability, by explicitly providing the knowledge and plan needed to solve a long-horizon task. First, we find that larger models can correctly execute significantly more turns even when small models have near-perfect single-turn accuracy. We then observe that the per-step accuracy of models degrades as the number of steps increases. This is not just due to long-context limitations---curiously, we observe a self-conditioning effect---models become more likely to make mistakes when the context contains their errors from prior turns. Self-conditioning does not reduce by just scaling the model size. But, we find that thinking mitigates self-conditioning, and also enables execution of much longer tasks in a single turn. We conclude by benchmarking frontier thinking models on the length of tasks they can execute in a single turn. Overall, by focusing on the ability to execute, we hope to reconcile debates on how LLMs can solve complex reasoning problems yet fail at simple tasks when made longer, and highlight the massive benefits of scaling model size and sequential test-time compute for long-horizon tasks.

Applications · Language, Speech and Dialog

Kohsei Matsutani, Shota Takashiro, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

Large language models (LLMs) are typically trained by reinforcement learning (RL) with verifiable rewards (RLVR) and supervised fine-tuning (SFT) on reasoning traces to improve their reasoning abilities. However, how these methods shape reasoning capabilities remains largely elusive. Going beyond an accuracy-based investigation of how these two components sculpt the reasoning process, this paper introduces a novel analysis framework that quantifies reasoning paths and captures their qualitative changes under each training process (with models of 1.5B, 7B, and 14B parameters on mathematical and code domains). Specifically, we investigate the reasoning process at two levels of granularity: the trajectory-level, which examines complete reasoning outputs, and the step-level, which analyzes reasoning graphs whose nodes correspond to individual reasoning steps. Notably, clustering of unique reasoning trajectories shows complementary effects: RL compresses incorrect trajectories, whereas SFT expands correct ones. Step-level analysis reveals that RL steepens (about 2.5 times), while SFT flattens (reduced to about one-third), the decay rates of node visitation frequency, degree, and betweenness centrality distributions in the reasoning graph. This indicates that RL concentrates reasoning functionality into a small subset of steps, while SFT homogenizes it across many steps. Furthermore, by evaluating the reasoning graph topologies from multiple perspectives, we delineate the shared and distinct characteristics of RL and SFT. Our work presents a novel reasoning path perspective that explains why the current best practice of two-stage training, with SFT followed by RL, is successful, and offers practical implications for data construction and more efficient learning approaches.

Optimization · Everything Else

Paul Caillon, Erwan Fagnou, Blaise Delattre, Alexandre Allauzen

Deep neural networks rely on backpropagation (BP) for optimization, but its strictly sequential backward pass hinders parallelism and scalability. Direct Feedback Alignment (DFA) has been proposed as a promising approach for parallel learning of deep neural networks, relying on fixed random projections to enable layer-wise parallel updates, but fails on deep convolutional networks, and performs poorly on modern transformer architectures. We introduce GrAPE (Gradient-Aligned Projected Error), a hybrid feedback-alignment method that (i) estimates rank-1 Jacobians via forward-mode JVPs and (ii) aligns each layer’s feedback matrix by minimizing a local cosine-alignment loss. To curb drift in very deep models, GrAPE performs infrequent BP anchor steps on a single mini-batch, preserving mostly parallel updates. We show that the forward-gradient estimator has strictly positive expected cosine with the true Jacobian. We relate this estimator-level guarantee to a standard stochastic-approximation result under a positive expected-cosine condition on the update direction, providing theoretical support for GrAPE’s alignment objective. Empirically, GrAPE consistently outperforms prior alternatives to BP, enabling the training of modern architectures, closing a large fraction of the gap to BP while retaining layer-parallel updates for the vast majority of steps.

Computer Vision · Vision Models & Multimodal

Tianqi Du, Lizhe Fang, Weijie Yang, Chenheng Zhang, Zeming Wei, Yifei Wang, Yisen Wang

Diffusion language models enable any-order generation and bidirectional conditioning, offering appealing flexibility for tasks such as infilling, rewriting, and self-correction. However, their formulation—predicting one part of a sequence from another within a single-step dependency—limits modeling depth and often yields lower sample quality and stability than autoregressive (AR) models. To address this, we revisit autoregressive modeling as a foundation and reformulate diffusion-style training into a structured multi-group prediction process. We propose Any-order Any-subset Autoregressive modeling (A3), a generalized framework that extends the standard AR factorization to arbitrary token groups and generation orders. A3 preserves the probabilistic rigor and multi-layer dependency modeling of AR while inheriting diffusion models' flexibility for parallel and bidirectional generation. We implement A3 through a two-stream attention architecture and a progressive adaptation strategy that transitions pretrained AR models toward any-order prediction. Experiments on question answering, commonsense reasoning, and story infilling demonstrate that A3 outperforms diffusion-based models while maintaining flexible decoding. This work offers a unified approach for a flexible, efficient, and novel language modeling paradigm. Code is at https://github.com/PKU-ML/Any-order-Any-subset-AR.

Social Aspects · Fairness, Equity, Justice and Safety

Rui Luo, Jie Bao, Xiaoyi Su, Wen Li, Suqun Cao

Current deep learning models for image segmentation often lack reliable uncertainty quantification, particularly at the image-specific level. While Conformal Risk Control (CRC) offers marginal statistical guarantees, achieving image-conditional coverage, which ensures prediction sets reliably capture ground truth for individual images, remains a significant challenge. This paper introduces a novel approach to address this gap by learning image-adaptive thresholds for conformal image segmentation. We first propose AT (Adaptive Thresholding), which frames threshold prediction as a supervised regression task. Building upon the insights from AT, we then introduce COAT (Conditional Optimization for Adaptive Thresholding), an innovative end-to-end differentiable framework. COAT directly optimizes image-conditional coverage by using a soft approximation of the True Positive Rate (TPR) as its loss function, enabling direct gradient-based learning of optimal image-specific thresholds. This novel differentiable miscoverage loss is key to enhancing conditional coverage. Our methods provide a robust pathway towards more trustworthy and interpretable uncertainty estimates in image segmentation, offering improved conditional guarantees crucial for safety-critical applications. The code is available at https://github.com/bjbbbb/Conditional-Optimization-for-Adaptive-Thresholding.

Reinforcement Learning · Multi-agent

Shirley Wu, Parth Sarthi, Shiyu Zhao, Aaron Lee, Herumb Shandilya, Adrian Mladenic Grobelnik, Nurendra Choudhary, Edward Huang, Karthik Subbian, Linjun Zhang 等

Compound AI systems integrating multiple components, such as Large Language Models, specialized tools, and traditional machine learning models, are increasingly deployed to solve complex real-world tasks. However, optimizing compound systems remains challenging due to their non-differentiable structures and diverse configuration types across components, including prompts, hyperparameters, and model parameters. To address this challenge, we propose Optimas, a unified framework for effective optimization of compound systems. The core idea of Optimas is to maintain one Local Reward Function (LRF) per component, each satisfying a local–global alignment property, i.e., each component’s local reward correlates with the global system performance. In each iteration, Optimas efficiently adapts the LRFs to maintain this property while simultaneously maximizing each component’s local reward. This approach enables independent updates of heterogeneous configurations using the designated optimization method, while ensuring that local improvements consistently lead to performance gains. We present extensive evaluations across five real-world compound systems to demonstrate that Optimas outperforms strong baselines by an average improvement of 11.92%, offering a general and effective approach for improving compound systems.

General Machine Learning · Representation Learning

Andy Arditi

Park et al., 2025 demonstrate that large language models can learn to trace random walks on graphs presented in context, and observe that token representations reorganize to reflect the underlying graph structure. This has been interpreted as evidence that models 'flexibly manipulate their representations' to reflect in-context semantics, and that this reorganization enables task performance. We offer a simpler mechanistic explanation. We first observe that task performance can be fully explained by induction circuits (Olsson et al., 2022), and show that ablating the attention heads that comprise these circuits substantially degrades performance. As for the geometric structure, we propose that it could result from previous token heads effectively mixing the representations of graph neighbors together. We show that a single round of such 'neighbor mixing' on random embeddings recreates the observed graph correspondence in PCA visualizations. These results suggest that apparent 'representation reorganization' may be a byproduct of the model's induction circuits, rather than a critical strategy useful for in-context learning.

Applications · Robotics

Gaole Dai, Shiqi Jiang, Ting Cao, Yuqing Yang, Yuanchun Li, Rui Tan, Mo Li, Lili Qiu

Reward is critical to the evaluation and training of large language models (LLMs). However, existing rule-based or model-based reward methods struggle to generalize to GUI agents, where access to ground-truth trajectories or application databases is often unavailable, and static trajectory-based LLM-as-a-Judge approaches suffer from limited accuracy. To address these challenges, we propose ProRe, a proactive reward system that leverages a general-purpose reasoner and domain-specific evaluator agents (actors). The reasoner schedules targeted state probing tasks, which the evaluator agents then execute by actively interacting with the environment to collect additional observations. This enables the reasoner to assign more accurate and verifiable rewards to GUI agents. Empirical results on over 3K trajectories demonstrate that ProRe improves reward accuracy and F1 score by up to 5.3\% and 19.4\%, respectively. Furthermore, integrating ProRe with state-of-the-art policy agents yields a success rate improvement of up to 22.4\%. The source code is available at https://github.com/V-Droid-Agent/ProRe.

General Machine Learning · Representation Learning

Yi-Ge Zhang, Jingyi Cui, Qiran Li, Yisen Wang

Unsupervised contrastive learning has shown significant performance improvements in recent years, often approaching or even rivaling supervised learning in various tasks. However, its learning mechanism is fundamentally different from supervised learning. Previous works have shown that difficult examples (well-recognized in supervised learning as examples around the decision boundary), which are essential in supervised learning, contribute minimally in unsupervised settings. In this paper, perhaps surprisingly, we find that the direct removal of difficult examples, although reduces the sample size, can boost the downstream classification performance of contrastive learning. To uncover the reasons behind this, we develop a theoretical framework modeling the similarity between different pairs of samples. Guided by this framework, we conduct a thorough theoretical analysis revealing that the presence of difficult examples negatively affects the generalization of contrastive learning. Furthermore, we demonstrate that the removal of these examples, and techniques such as margin tuning and temperature scaling can enhance its generalization bounds, thereby improving performance. Empirically, we propose a simple and efficient mechanism for selecting difficult examples and validate the effectiveness of the aforementioned methods, which substantiates the reliability of our proposed theoretical framework.

Reinforcement Learning · Everything Else

Zaid Khan, Archiki Prasad, Elias Stengel-Eskin, Jaemin Cho, Mohit Bansal

Symbolic world modeling is the task of inferring and representing the transitional dynamics of an environment as an executable program. Previous research on symbolic world modeling has focused on simple, deterministic environments with abundant data and human-provided guidance. We address the more realistic and challenging problem of learning a symbolic world model in a complex, stochastic environment with severe constraints: a limited interaction budget where the agent has only “one life” to explore a hostile environment and no external guidance in the form of human-provided, environment-specific rewards or goals. We introduce OneLife, a framework that models world dynamics through conditionally-activated programmatic laws within a probabilistic programming framework. Each law operates through a precondition-effect structure, allowing it to remain silent on irrelevant aspects of the world state and predict only the attributes it directly governs. This creates a dynamic computation graph that routes both inference and optimization only through relevant laws for each transition, avoiding the scaling challenges that arise when all laws must contribute to predictions about a complex, hierarchical state space, and enabling accurate learning of stochastic dynamics even when most rules are inactive at any given moment. To evaluate our approach under these demanding constraints, we introduce a new evaluation protocol that measures (a) state ranking, the ability to distinguish plausible future states from implausible ones, and (b) state fidelity, the ability to generate future states that closely resemble reality. We develop and evaluate our framework on Crafter-OO, our reimplementation of the popular Crafter environment that exposes a structured, object-oriented symbolic state and and a pure transition function that operates on that state alone. OneLife can successfully learn key environment dynamics from minimal, unguided interaction, outperforming a strong baseline on 16 out of 23 scenarios tested. We also demonstrate the world model’s utility for planning, where rollouts simulated within the world model successfully identify superior strategies in multi-step goal-oriented tasks. Our work establishes a foundation for autonomously constructing programmatic world models of unknown, complex environments.

Applications · Language, Speech and Dialog

Haozhe Wang, Haoran Que, Qixin Xu, Minghao Liu, Wangchunshu Zhou, Jiazhan Feng, Wanjun Zhong, Wei Ye, Tong Yang, Wenhao Huang 等

While the "deep reasoning" paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling reasoning—reinforcement learning (RL) and instruction distillation -- falter in this area; RL struggles with the absence of clear reward signals and high-quality reward models, while distillation is prohibitively expensive and capped by the teacher model's capabilities. To overcome these limitations, we introduce REverse-Engineered Reasoning (REER), a new paradigm that fundamentally shifts the approach. Instead of building a reasoning process "forwards" through trial-and-error or imitation, REER works "backwards" from known good solutions to computationally discover the latent, step-by-step deep reasoning process that could have produced them. Using this scalable, gradient-free approach, we curate and open-source DeepWriting-20K, a large-scale dataset of 20,000 deep reasoning trajectories for open-ended tasks. Our model, DeepWriter-8B, trained on this data, not only surpasses strong open-source baselines but also achieves performance competitive with, and at times superior to, leading proprietary models like GPT-4o and Claude 3.5.

Social Aspects · Fairness, Equity, Justice and Safety

Geon-Hyeong Kim, Yu Jin Kim, Byoungjip Kim, Honglak Lee, Kyunghoon Bae, Youngsoo Jang, Moontae Lee

As Large Language Models (LLMs) are increasingly deployed in real-world applications, balancing helpfulness and safety has become a central challenge. A natural approach is to incorporate safety constraints into Reinforcement Learning from Human Feedback (RLHF), where recent studies have shown promising progress. However, these methods often rely on auxiliary networks or multi-stage pipelines, thereby increasing complexity. In this work, we revisit the original safety alignment objective and show that, under mild assumptions, it admits a closed-form optimal policy. We further derive a provably equivalent and tractable objective, enabling direct optimization. Building on this insight, we propose SafeDPO, a lightweight method that preserves the optimal solution of the underlying safety-constrained objective while requiring only one additional hyperparameter and minimal modifications to existing preference-based training methods. SafeDPO eliminates the need for reward models, cost models, and online sampling, relying only on preference data and safety indicators. Despite its simplicity, SafeDPO achieves competitive safety–helpfulness trade-offs compared to existing safety alignment methods. Experiments on the PKU-SafeRLHF-30K benchmark demonstrate that SafeDPO substantially improves safety while maintaining competitive helpfulness. Ablation studies further show that the additional hyperparameter provides a flexible mechanism to enhance safety while preserving the theoretical optimum, and confirm that SafeDPO scales reliably to LLMs with up to 13B parameters. Overall, our results highlight that a simple, theory-driven objective can provide a lightweight yet effective solution for safety alignment in practice.

Reinforcement Learning · Deep RL

Jiazhan Feng, Shijue Huang, Xingwei Qu, Ge Zhang, Yujia Qin, Baoquan Zhong, Chengquan Jiang, Jinxin Chi, Wanjun Zhong

While reasoning models trained with reinforcement learning (RL) excel in reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric reasoning, concise computation, or complex equation solving—areas where computational tools like code interpreters (CI) demonstrate distinct advantages. To bridge this gap, we propose ReTool, which enhances long-form reasoning with tool-integrated learning, including two key features: (1) dynamic interleaving of real-time code execution within natural language reasoning processes, and (2) an automated RL paradigm that allows policy rollouts with multi-turn real-time code execution and teaches the model in learning when and how to invoke tools based on outcome feedback. ReTool employs a systematic training framework, beginning with synthetic code-augmented long-form reasoning data for cold-start training. Subsequent RL training leverages task outcomes as rewards to iteratively refine the model's tool use strategy, enabling autonomous discovery of optimal tool invocation patterns without human priors. Experiments on challenging MATH Olympiad benchmark AIME demonstrate ReTool's superiority: Our 32B model achieves 67% accuracy with 400 training steps, outperforming text-based RL baseline (40% accuracy, 1080 steps) in performance and efficiency. Remarkably, ReTool-32B attains 72.5% accuracy in extended settings, surpassing OpenAI's o1-preview by 27.9%. Further analysis reveals generalization to broader tool-use scenarios and emergent behaviors such as code self-correction, signaling an ''aha moment'' in which the model autonomously masters adaptive tool use. These findings highlight the promise of outcome-driven tool integration for advancing complex mathematical reasoning and offer new insights into hybrid neuro-symbolic systems.

Applications · Language, Speech and Dialog

Victor Wang, Elias Stengel-Eskin

Calibrated confidence estimates are necessary for large language model (LLM) outputs to be trusted by human users. While LLMs can express their confidence in human-interpretable ways, verbalized LLM-generated confidence scores have empirically been found to be miscalibrated, reporting high confidence on instances with low accuracy and thereby harming trust and safety. We hypothesize that this overconfidence often stems from a given LLM’s heightened suggestibility when faced with claims that it encodes little information about; we empirically validate this hypothesis, finding more suggestibility on lower-accuracy claims. Building on this finding, we introduce Distractor-Normalized Coherence (DINCO), which estimates and accounts for an LLM’s suggestibility bias by having the model verbalize its confidence independently across several self-generated distractors (i.e. alternative claims), and normalizes by the total verbalized confidence. To further improve calibration, we leverage generator-validator disagreement, augmenting normalized validator confidence with a consistency-based estimate of generator confidence. Here, we frame the popular approach of self-consistency as leveraging coherence across sampled generations, and normalized verbalized confidence as leveraging coherence across validations on incompatible claims, allowing us to integrate these complementary dimensions of coherence into DINCO. Moreover, our analysis shows that DINCO provides less saturated – and therefore more usable – confidence estimates, and that further sampling alone cannot close the gap between DINCO and baselines, with DINCO at 10 runs outperforming self-consistency at 100. We release our code at https://github.com/victorwang37/dinco.