论文检索

Social Aspects · Accountability, Transparency and Interpretability

Brian Christian, Jessica Thompson, Elle Michelle Yang, Vincent Adam, Hannah Kirk, Christopher Summerfield, Tsvetomira Dumbalska

Reward models (RMs) are central to aligning large language models (LLMs) with human values but have received less attention than pretrained and post-trained LLMs themselves. Because RMs are initialized from LLMs, they inherit representations that shape their behavior, but the nature and extent of this influence remain understudied. In a comprehensive study of 10 leading open-weight RMs using validated psycholinguistic corpora, we show that RMs exhibit significant differences along multiple dimensions of human value as a function of their base model. Using the "Big Two" psychological axes, we show a robust preference of Llama RMs for "agency" and a corresponding robust preference of Gemma RMs for "communion." This phenomenon holds even when the preference data and finetuning process are identical, and we trace it back to the logits of the respective instruction-tuned and pretrained models. These log-probability differences themselves can be formulated as an implicit RM; we derive usable implicit reward scores and show that they exhibit the very same agency/communion difference. We run experiments training RMs with ablations for preference data source and quantity, which demonstrate that this effect is not only repeatable but surprisingly durable. Despite RMs being designed to represent human preferences, our evidence shows that their outputs are influenced by the pretrained LLMs on which they are based. This work underscores the importance of safety and alignment efforts at the pretraining stage, and makes clear that open-source developers' choice of base model is as much a consideration of values as of performance.

Deep Learning · Everything Else

Mark Rofin, Jalal Naghiyev, Michael Hahn

Trained Transformers have been shown to compute abstract features that appear redundant for predicting the immediate next token. We identify which components of the gradient signal from the next-token prediction objective give rise to this phenomenon, and we propose a method to estimate the influence of those components on the emergence of specific features. After validating our approach on toy tasks, we use it to interpret the origins of the world model in OthelloGPT and syntactic features in a small language model. Finally, we apply our framework to a pretrained LLM, showing that features with extremely high or low influence on future tokens tend to be related to formal reasoning domains such as code. Overall, our work takes a step toward understanding hidden features of Transformers through the lens of their development during training.

Computer Vision · Classification and Understanding

Jiajing Lin, Shu Jiang, Qingyuan Zeng, Zhenzhong Wang, Min Jiang

The intrinsic dynamics of an object governs its physical behavior in the real world, playing a critical role in enabling physically plausible interactive simulation with 3D assets. Existing methods have attempted to infer the intrinsic dynamics of objects from visual observations, but generally face two major challenges: one line of work relies on manually defined constitutive priors, making it difficult to align with actual intrinsic dynamics; the other models intrinsic dynamics using neural networks, resulting in limited interpretability and poor generalization. To address these challenges, we propose VisionLaw, a bilevel optimization framework that infers interpretable expressions of intrinsic dynamics from visual observations. At the upper level, we introduce an LLMs-driven decoupled constitutive evolution strategy, where LLMs are prompted to act as physics experts to generate and revise constitutive laws, with a built-in decoupling mechanism that substantially reduces the search complexity of LLMs. At the lower level, we introduce a vision-guided constitutive evaluation mechanism, which utilizes visual simulation to evaluate the consistency between the generated constitutive law and the underlying intrinsic dynamics, thereby guiding the upper-level evolution. Experiments on both synthetic and real-world datasets demonstrate that VisionLaw can effectively infer interpretable intrinsic dynamics from visual observations. It significantly outperforms existing state-of-the-art methods and exhibits strong generalization for interactive simulation in novel scenarios.

Deep Learning · Graph Neural Networks

Jingyao Wu, Bin Lu, Zijun Di, Xiaoying Gan, Meng Jin, Luoyi Fu, Xinbing Wang, Chenghu Zhou

Large language models show great potential in unstructured data understanding, but still face significant challenges with graphs due to their structural hallucination. Existing approaches mainly either verbalize graphs into natural language, which leads to excessive token consumption and scattered attention, or transform graphs into trainable continuous embeddings (i.e., soft prompt), but exhibit severe misalignment with original text tokens. To solve this problem, we propose to incorporate one special token to fully represent the \textbf{\underline{S}}tructure \textbf{\underline{O}}f \textbf{\underline{G}}raph within a unified token space, facilitating explicit topology input and structural information sharing. Specifically, we propose a topology-aware structural tokenizer that maps each graph topology into a highly selective single token. Afterwards, we construct a set of hybrid structure Question-Answering corpora to align new structural tokens with existing text tokens. With this approach, empowers LLMs to understand, generate, and reason in a concise and accurate manner. Extensive experiments on five graph-level benchmarks demonstrate the superiority of our method, achieving a performance improvement of 9.9–41.4\% compared to the baselines while exhibiting interpretability and consistency. Furthermore, our method provides a flexible extension to node-level tasks, enabling both global and local structural understanding. The codebase is publicly available\footnote{The code of our project is available at \href{https://anonymous.4open.science/r/SOG-8432}{https://anonymous.4open.science/r/SOG-8432}.}.

Theory · Interpretability and Visualization

Marco Bondaschi, Nived Rajaraman, Xiuying Wei, Razvan Pascanu, Caglar Gulcehre, Michael Gastpar, Ashok Makkuva

While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viable alternatives, such as structured state space sequence models (SSMs) and Selective SSMs. Among these, Mamba (S6) and its variant Mamba-2 have shown remarkable inference speed-ups over transformers while achieving comparable or superior performance on complex language modeling tasks. However, despite these architectural innovations and empirical successes, the fundamental learning capabilities of Mamba remain poorly understood. In this paper, we address this gap by studying in-context learning (ICL) on Markov chains and uncovering an interesting phenomenon: even a single-layer Mamba efficiently learns the in-context Laplacian smoothing estimator, which is both Bayes and minimax optimal. To explain this, we theoretically characterize the representation capacity of Mamba and reveal the fundamental role of convolution in enabling it to represent the optimal Laplacian smoothing. These theoretical insights align strongly with empirical results and, to the best of our knowledge, represent the first formal connection between Mamba and optimal statistical estimators. Finally, we outline promising research directions inspired by these findings.

Social Aspects · Trustworthy Machine Learning

Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Aidong Zhang

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generations contradict or extend beyond the provided sources, remain a critical challenge. Existing hallucination detection methods for RAG often rely either on large-scale detector training, which requires substantial annotated data, or on querying external LLM judges, which leads to high inference costs. Although some approaches attempt to leverage internal representations of LLMs for hallucination detection, their accuracy remains limited. Motivated by recent advances in mechanistic interpretability, we employ sparse autoencoders (SAEs) to disentangle internal activations, successfully identifying features that are specifically triggered during RAG hallucinations. Building on a systematic pipeline of information-based feature selection and additive feature modeling, we introduce RAGLens, a lightweight hallucination detector that accurately flags unfaithful RAG outputs using LLM internal representations. RAGLens not only achieves superior detection performance compared to existing methods, but also provides interpretable rationales for its decisions, enabling effective post-hoc mitigation of unfaithful RAG. Finally, we justify our design choices and reveal new insights into the distribution of hallucination-related signals within LLMs. The code is available at https://github.com/Teddy-XiongGZ/RAGLens.

Applications · Language, Speech and Dialog

Jiayu Wang, Yifei Ming, Riya Dulepet, Qinglin Chen, Austin Xu, Zixuan Ke, Frederic Sala, Aws Albarghouthi, Caiming Xiong, Shafiq Joty

Deep research---producing comprehensive, citation-backed reports by searching across hundreds of live websites---marks an important frontier for agentic systems. To rigorously evaluate this ability, three principles are essential: tasks should be (1) user-centric, reflecting realistic information needs, (2) dynamic, requiring up-to-date information beyond parametric knowledge, and (3) unambiguous, ensuring consistent interpretation across users. Existing benchmarks fall short of these principles, often focusing on narrow domains or posing ambiguous questions that hinder fair comparison. Guided by these principles, we introduce LiveResearchBench, a benchmark of 100 expert-curated tasks spanning daily life, enterprise, and academia, each requiring extensive, dynamic, real-time web search and synthesis. Built with over 1,500 hours of human labor, LiveResearchBench provides a rigorous basis for systematic evaluation. To evaluate citation-grounded long-form reports, we present DeepEval, a comprehensive suite covering both content- and report-level quality: checklists for coverage and presentation, rubric-tree assessments of citation accuracy and traceability, and metrics for consistency and depth of analysis. Using LiveResearchBench and DeepEval, we conduct a comprehensive evaluation of frontier deep research systems, including single-agent web search, single-agent deep research, and multi-agent systems. Our analysis reveals current strengths, recurring failure modes, and key system components needed to advance reliable, insightful deep research. Our code is available at: https://github.com/SalesforceAIResearch/LiveResearchBench.

Social Aspects · Accountability, Transparency and Interpretability

Gonçalo Paulo, Nora Belrose

Sparse autoencoders (SAEs) are a useful tool for uncovering human-interpretable features in the activations of large language models (LLMs). While some expect SAEs to find the true underlying features used by a model, our research shows that SAEs trained on the same model and data, differing only in the random seed used to initialize their weights, identify different sets of features. For example, in an SAE with 131K latents trained on a feedforward network in Llama 3 8B, only 30\% of the features were shared across different seeds. We observed this phenomenon across multiple layers of three different LLMs, two datasets, and several SAE architectures. While ReLU SAEs trained with the L1 sparsity loss showed greater stability across seeds, SAEs using the state-of-the-art TopK activation function were more seed-dependent, even when controlling for the level of sparsity. Our results suggest that the set of features uncovered by an SAE should be viewed as a pragmatically useful decomposition of activation space, rather than an exhaustive and universal list of features ``truly used'' by the model.

Social Aspects · Accountability, Transparency and Interpretability

Gonçalo Paulo, Nora Belrose

Sparse autoencoders (SAEs) and transcoders have become important tools for machine learning interpretability. However, measuring how interpretable they are remains challenging, with weak consensus about which benchmarks to use. Most evaluation procedures start by producing a single-sentence explanation for each latent. These explanations are then evaluated based on how well they enable an LLM to predict the activation of a latent in new contexts. This method makes it difficult to disentangle the explanation generation and evaluation process from the actual interpretability of the latents discovered. In this work, we adapt existing methods to assess the interpretability of sparse coders, with the advantage that they do not require generating natural language explanations as an intermediate step. This enables a more direct and potentially standardized assessment of interpretability. Furthermore, we compare the scores produced by our interpretability metrics with human evaluations across similar tasks and varying setups, offering suggestions for the community on improving the evaluation of these techniques.

Social Aspects · Accountability, Transparency and Interpretability

Sayan Saha, Sanghamitra Bandyopadhyay

Model-level explanations for Graph Neural Networks (GNNs) aim to identify class-discriminative motifs that capture how a classifier recognizes a target class. Because the true motifs relied on by the classifier are unobservable, most approaches evaluate explanations by their target class score. However, class score alone is not sufficient as high-scoring explanations may be pathological or may fail to reflect the full range of motifs recognized by the classifier. To bridge this gap, this work introduces sufficiency risk as a formal criterion for whether explanations adequately represent the classifier’s reasoning, and derives distribution-free certificates that upper-bound this risk. Building on this foundation, three metrics are introduced: Coverage, Greedy Gain Area (GGA), and Overlap which operationalize the certificates to assess sufficiency, efficiency, and redundancy in explanations. To ensure practical utility, finite-sample concentration bounds are developed for these metrics, providing confidence intervals that enable statistically reliable comparison between explainers. Experiments on synthetic data and with three state-of-the-art explainers on four real-world datasets demonstrate that these metrics reveal differences in explanation quality hidden by class scores alone. Designed to complement class score, they constitute the first theoretically certified framework for evaluating model-level explanations of GNNs.

Theory · Probabilistic Methods

Madi Matymov, Ba-Hien Tran, Michael Kampffmeyer, Markus Heinonen, Maurizio Filippone

Data Augmentation (DA) has become an essential tool to improve robustness and generalization of modern machine learning. However, when deciding on DA strategies it is critical to choose parameters carefully, and this can be a daunting task which is traditionally left to trial-and-error or expensive optimization based on validation performance. In this paper, we counter these limitations by proposing a novel framework for optimizing DA. In particular, we take a probabilistic view of DA, which leads to the interpretation of augmentation parameters as model (hyper)-parameters, and the optimization of the marginal likelihood with respect to these parameters as a Bayesian model selection problem. Due to its intractability, we derive a tractable ELBO, which allows us to optimize augmentation parameters jointly with model parameters. We provide extensive theoretical results on variational approximation quality, generalization guarantees, invariance properties, and connections to empirical Bayes. Through experiments on computer vision and NLP tasks, we show that our approach improves calibration and yields robust performance over fixed or no augmentation. Our work provides a rigorous foundation for optimizing DA through Bayesian principles with significant potential for robust machine learning.

Theory · Interpretability and Visualization

Yufeng Zhang, Xuepeng Wang, Lingxiang Wu, Jinqiao Wang

While chain-of-thought prompting enables powerful multi-step reasoning in Large Language Models (LLMs), the stochastic nature of the generation process undermines its reliability. In this work, we first analyze thousands of reasoning paths to identify Reasoning Drift, a key failure mode where models get locked into flawed reasoning patterns. We reveal that the manifestation of drift is a complex interplay between universal functional tendencies and unique, model-specific signatures. Based on the diagnosis, we propose Reasoning-Aware Activation Steering, a novel inference-time intervention method to gently nudge the model's activations away from pathological patterns. We pre-compute a library of vectors from contrastive functional transitions and apply them dynamically. Experiments show that our method effectively mitigates the drift problem and boosts accuracy. Additionally, it generalizes to out-of-distribution tasks, demonstrating a deeper capture of valid reasoning principles.

General Machine Learning · Representation Learning

Vivek Anand, Alec Helbling, Mark Davenport, Gordon Berman, Sankaraleengam Alagapan, Christopher Rozell

Learning the intrinsic dimensionality of subjective perceptual spaces such as taste, smell, or aesthetics from ordinal data is a challenging problem. We introduce LORE (Low Rank Ordinal Embedding), a scalable framework that jointly learns both the intrinsic dimensionality and an ordinal embedding from noisy triplet comparisons of the form, "Is A more similar to B than C?". Unlike existing methods that require the embedding dimension to be set apriori, LORE regularizes the solution using the nonconvex Schatten-$p$ quasi norm, enabling automatic joint recovery of both the ordinal embedding and its dimensionality. We optimize this joint objective via an iteratively reweighted algorithm and establish convergence guarantees. Extensive experiments on synthetic datasets, simulated perceptual spaces, and real world crowdsourced ordinal judgements show that LORE learns compact, interpretable and highly accurate low dimensional embeddings that recover the latent geometry of subjective percepts. By simultaneously inferring both the intrinsic dimensionality and ordinal embeddings, LORE enables more interpretable and data efficient perceptual modeling in psychophysics and opens new directions for scalable discovery of low dimensional structure from ordinal data in machine learning.

Applications · Health

Anjie Le, Henan Liu, Yue Wang, Zhenyu Liu, Rongkun Zhu, Taohan Weng, Jinze Yu, Boyang Wang, Yalun Wu, Kaiwen Yan 等

Ultrasound is a widely-used imaging modality critical to global healthcare, yet its interpretation remains challenging due to its varying image quality on operators, noises, and anatomical structures. Although large vision-language models (LVLMs) have demonstrated impressive multimodal capabilities across natural and medical domains, their performance on ultrasound remains largely unexplored. We introduce U2-BENCH, the first comprehensive benchmark to evaluate LVLMs on ultrasound understanding across classification, detection, regression, and text generation tasks. U2-BENCH aggregates 7,241 cases spanning 15 anatomical regions and defines 8 clinically inspired tasks, such as diagnosis, view recognition, lesion localization, clinical value estimation, and report generation, across 50 ultrasound application scenarios. We evaluate 23 state-of-the-art LVLMs, both open- and closed-source, general-purpose and medical-specific. Our results reveal strong performance on image-level classification, but persistent challenges in spatial reasoning and clinical language generation. U2-BENCH establishes a rigorous and unified testbed to assess and accelerate LVLM research in the uniquely multimodal domain of medical ultrasound imaging.

Theory · Interpretability and Visualization

Hongxu Liu, Jing Ma, Xiaojie Wang, Caixia YUAN, Fangxiang Feng

Figuring out how neural language models comprehend syntax acts as a key to revealing how they understand languages. We systematically analyzed methods for finding syntax structures in models, namely _probing_, and found limitations yet widely exist in previous probing practice. We proposed a method capable of estimating mutual information (MI) and extracting dependency trees from attention scores in a mathematical-rigorous way, requiring no additional network training effort. Compared with previous approaches, it has a much simpler model, while being able to probe more complex dependency trees, also transparent for fine-grained explanation. We tested our method on several open-source LLMs and demonstrated its effectiveness by systematically comparing it with a great many competitive baselines. Several informative conclusions can be drawn by further analysis of the results, shedding light on our method’s explanatory potential. Our code is released at https://github.com/ChristLBUPT/IPBP.

General Machine Learning · Probabilistic Methods

Puhua Niu, Shili Wu, Xiaoning Qian

Generative Flow Networks (GFlowNets) were developed to learn policies for efficiently sampling combinatorial candidates by interpreting their generative processes as trajectories in directed acyclic graphs. In the value-based training workflow, the objective is to enforce the balance over partial episodes between the flows of the learned policy and the estimated flows of the desired policy, implicitly encouraging policy divergence minimization. The policy-based strategy alternates between estimating the policy divergence and updating the policy, but reliable estimation of the divergence under directed acyclic graphs remains a major challenge. This work bridges the two perspectives by showing that flow balance also yields a principled policy evaluator that measures the divergence, and an evaluation balance objective over partial episodes is proposed for learning the evaluator. As demonstrated on both synthetic and real-world tasks, evaluation balance not only strengthens the reliability of policy-based training but also broadens its flexibility by seamlessly supporting parameterized backward policies and enabling the integration of offline data-collection techniques. Our code is available at [github.com/niupuhua1234/Sub-EB](https://github.com/niupuhua1234/Sub-EB).

Social Aspects · Accountability, Transparency and Interpretability

Jingtong Su, Julia Kempe, Karen Ullrich

Transformers have achieved state-of-the-art performance across diverse language and vision tasks. This success drives the imperative to interpret their internal mechanisms with the dual goals of enhancing performance and improving behavioral control. Attribution methods help advance interpretability by assigning model outputs associated with a target concept to specific model components. Current attribution research primarily studies multi-layer perceptron (MLP) neurons and addresses relatively simple concepts such as factual associations (e.g., Paris is located in France). This focus tends to overlook the impact of the attention mechanism and lacks a unified approach for analyzing more complex concepts. To fill these gaps, we introduce Scalable Attention Module Discovery (SAMD), a concept-agnostic method for mapping arbitrary, complex concepts to specific attention heads of general transformer models. We accomplish this by representing each concept as a vector, calculating its cosine similarity with each attention head, and selecting the TopK-scoring heads to construct the concept-associated attention module. We then propose Scalar Attention Module Intervention (SAMI), a simple strategy to diminish or amplify the effects of a concept by adjusting the attention module using only a single scalar parameter. Empirically, we demonstrate SAMD on concepts of varying complexity, and visualize the locations of their corresponding modules. Our results demonstrate that module locations remain stable before and after LLM post-training, and confirm prior work on the mechanics of LLM multi-lingualism. Through SAMI, we facilitate jailbreaking on HarmBench (+72.7%) by diminishing “safety” and improve performance on the GSM8K benchmark (+1.6%) by amplifying “reasoning”. Lastly, we highlight the domain-agnostic nature of our approach by suppressing the image classification accuracy of vision transformers on ImageNet.

Computer Vision · 3D Rendering & Reconstruction

Dmitrii Pozdeev, Alexey Artemov, Ananta R. Bhattarai, Artem Sevastopolsky

We propose DenseMarks -- a new learned representation for human heads, enabling high-quality dense correspondences of human head images. For a 2D image of a human head, a Vision Transformer network predicts a 3D embedding for each pixel, which corresponds to a location in a 3D canonical unit cube. In order to train our network, we collect a dataset of pairwise point matches, estimated by a state-of-the-art point tracker over a collection of diverse in-the-wild talking heads videos, and guide the mapping via a contrastive loss, encouraging matched points to have close embeddings. We further employ multi-task learning with face landmarks and segmentation constraints, as well as imposing spatial continuity of embeddings through latent cube features, which results in an interpretable and queryable canonical space. The representation can be used for finding common semantic parts, face/head tracking, and stereo reconstruction. Due to the strong supervision, our method is robust to pose variations and covers the entire head, including hair. Additionally, the canonical space bottleneck makes sure the obtained representations are consistent across diverse poses and individuals. We demonstrate state-of-the-art results in geometry-aware point matching and monocular head tracking with 3D Morphable Models. The code and the model checkpoint will be made available to the public.

Theory · Interpretability and Visualization

Giordano Ramos-Traslosheros, Carlos Ponce

Signed connectivity is fundamental to neural computation in both brains (excitatory/inhibitory) and machines (positive/negative). Yet the role of signed weights in shaping visual representations in object recognition remains unclear. Dale's Law, the biological principle that neurons send exclusively excitatory or inhibitory outputs, is typically not enforced in artificial neural networks (ANNs). Here, we find that accuracy in ImageNet-trained ANNs correlates with the spontaneous emergence of sign-specific "Dale-like" segregation in their output layers. Ablation and feature visualization reveal a functional segregation in ANNs: removing positive inputs primarily disrupts localized, object-related structure, while removing negative inputs alters mainly dispersed background textures. This segregation is more pronounced in adversarially robust models, persists with unsupervised learning, and vanishes with non-rectified activation functions. We validate these observations in the macaque ventral visual cortex (V1, V4, and IT) using encoding models and in vivo feature visualization. The features recovered by encoding models qualitatively matched those identified in vivo. Model representations changed more upon positive than negative input ablations. We analyzed the most Dale-like units across neuron models, positive units showed localized features, while negative units showed larger, more dispersed features. Consistent with this, experimentally clearing the background around a neuron's preferred feature enhanced its response, likely by reducing inhibitory drive. Our results suggest that both artificial and biological vision systems segregate features by weight sign: positive weights emphasize object-related features, while negative weights refine context. This highlights a convergent representational strategy in brains and machines, yielding predictions for visual neuroscience.

Applications · Robotics

Yiteng Chen, Huiping Zhuang, Wenbo Li, Shiyi Wang, Xiangyu Zhao, Qingyao Wu

In recent years, robotic manipulation policies have made substantial progress. However, evaluating these policies typically requires large-scale sampling in simulation benchmarks, leading to high time costs. Moreover, existing evaluation pipelines are usually fixed, do not account for user needs, and report only a single scalar score, lacking interpretability. In contrast, human experts can quickly form an intuitive impression of a policy’s capabilities from just a handful of executions. We therefore propose ManipEvalAgent, an efficient, promptable, and dynamically multi-round evaluation framework for robotic manipulation policies. The framework conducts small-batch, multi-round evaluations and adaptively plans subsequent evaluation steps based on intermediate observations from each round. Via code generation, it constructs tasks and evaluation functions within simulator. By generating evaluation functions and leveraging vision–language models (VLMs) for video understanding, ManipEvalAgent provides user-instruction-centric, fine-grained analysis. Our approach offers three key advantages: (1) efficiency, no need for massive sampling; (2) promptable, planning the evaluation process according to user queries; and (3) interpretability, providing diagnostic text that goes beyond a single score. Across multiple settings, our evaluation method significantly shortens the overall time compared with traditional simulation benchmarks, while reaching conclusions comparable to those from large-scale simulation benchmarks.