论文检索

Computer Vision · Vision Models & Multimodal

Yilun Hao, Yongchao Chen, Chuchu Fan, Yang Zhang

Vision Language Models (VLMs) show strong potential for visual planning but struggle with precise spatial and long-horizon reasoning, while Planning Domain Definition Language (PDDL) planners excel at formal long-horizon planning but cannot interpret visual inputs. Recent works combine these complementary advantages by translating visual problems into PDDL. However, while VLMs can generate PDDL problem files satisfactorily, accurately generating PDDL domain files, which encode planning rules, remains challenging and typically requires human expertise or environment interaction. We propose VLMFP, a Dual-VLM-guided framework that autonomously generates both PDDL problem and domain files for formal visual planning. VLMFP combines a SimVLM that simulates action consequences with a GenVLM that generates and iteratively refines PDDL files by aligning symbolic execution with simulated outcomes, enabling multiple levels of generalization across unseen instances, visual appearances, and game rules. We evaluate VLMFP on 6 grid-world domains and demonstrate its generalization capability. On average, SimVLM achieves 87.3\% and 86.0\% scenario understanding and action simulation for seen and unseen appearances, respectively. With the guidance of SimVLM, VLMFP attains 70.0\%, 54.1\% planning success on unseen instances in seen and unseen appearances, respectively. We further demonstrate that VLMFP scales to complex long-horizon 3D planning tasks, including multi-robot collaboration and assembly scenarios with partial observability and diverse visual variations. Project page: https://sites.google.com/view/vlmfp.

Theory · Interpretability and Visualization

Jim Maar, Denis Paperno, Callum McDougall, Neel Nanda

Prior work suggests that language models, while trained on next token prediction, show implicit planning behavior: they may select the next token in preparation to a predicted future token, such as a likely rhyming word, as supported by a prior qualitative study of Claude 3.5 Haiku using a cross-layer transcoder. We propose much simpler techniques for assessing implicit planning in language models. With case studies on rhyme poetry generation and question answering, we demonstrate that our methodology easily scales to many models. Across models, we find that the generated rhyme (e.g. "-ight") or answer to a question ("whale") can be manipulated by steering at the end of the preceding line with a vector, affecting the generation of intermediate tokens leading up to the rhyme or answer word. We show that implicit planning is a universal mechanism, present in smaller models than previously thought, starting from 1B parameters. Our methodology offers a widely applicable direct way to study implicit planning abilities of LLMs. More broadly, understanding planning abilities of language models can inform decisions in AI safety and control.

Applications · Health

Zonghai Yao, Benlu Wang, Yifan Zhang, Junda Wang, Iris Xia, Zhipeng Tang, Shuo Han, Feiyun, Zhichao Yang, Arman Cohan 等

Large language models perform well on many medical QA benchmarks, but real clinical reasoning is harder because diagnosis often requires integrating evidence across multiple images rather than interpreting a single view. We introduce MedThinkVQA, an expert-annotated benchmark for thinking with multiple images, in which models must interpret each image, combine cross-view evidence, and solve diagnostic questions under intermediate supervision and step-level evaluation. The dataset contains 10,067 cases, including 720 test cases, with an average of 6.68 images per case, substantially denser than prior work (earlier maxima $\leq$ 1.43). On the test set, the best closed-source models, Claude-4.6-opus, Gemini-3-pro, and GPT-5.2-xhigh, achieve only 54.9%--57.2% accuracy, while smaller proprietary variants, GPT-5-mini/nano, drop to 39.7% and 30.8%. Top open-source models perform worse overall, with Qwen3.5-397B-A17B (52.2%) and Qwen3.5-27B (50.6%) leading, followed by Lingshu-32B (43.2%), InternVL3.5-38B (40.7%), and MedGemma-27B (31.8%). Further analysis points to a single-core bottleneck: current models struggle with grounded multi-image reasoning, i.e., reliably extracting, aligning, and composing evidence across views before higher-level inference can help. This is supported by three consistent findings: adding expert-provided single-image cues and integrating cross-image evidence improve performance, whereas replacing them with models’ self-generated intermediates reduces accuracy. Step-level analysis shows that over 70% of errors come from image reading and cross-view integration, with reasoning failures increasing on decisive steps. Scaling results show that while accuracy increases with more images, additional inference-time computation is beneficial only when the underlying visual grounding is already reliable. When early evidence extraction is weak, longer reasoning yields limited or unstable gains and can even amplify misread cues. Together, these results show that the main barrier is not simply insufficient reasoning length or depth, but the lack of reliable mechanisms for grounding, aligning, and composing distributed evidence across real-world, cross-view, multimodal clinical inputs.

Computer Vision · Vision Models & Multimodal

Yikun Ji, Yan Hong, Qi Fan, jun lan, Huijia Zhu, Weiqiang Wang, Liqing Zhang, Jianfu Zhang

The rapid rise of image generation calls for detection methods that are both interpretable and reliable. Existing approaches, though accurate, act as black boxes and fail to generalize to out-of-distribution data, while multi-modal large language models (MLLMs) provide reasoning ability but often hallucinate. To address these issues, we construct \textbf{FakeXplained} dataset of AI-generated images annotated with bounding boxes and descriptive captions that highlight synthesis artifacts, forming the basis for human-aligned, visually grounded reasoning. Leveraging \textbf{FakeXplained}, we develop \textbf{FakeXplainer} which fine-tunes MLLMs with a progressive training pipeline, enabling accurate detection, artifact localization, and coherent textual explanations. Extensive experiments show that \textbf{FakeXplainer} not only sets a new state-of-the-art in detection and localization accuracy ($98.2\%$ accuracy, $36.0\%$ IoU), but also demonstrates strong robustness and out-of-distribution generalization, uniquely delivering spatially grounded, human-aligned rationales. The code and dataset are available at: \href{https://github.com/Gennadiyev/FakeXplain}{https://github.com/Gennadiyev/FakeXplain}.

Theory · Interpretability and Visualization

Joshua Melander, Zaki Alaoui, Shenghua Liu, Surya Ganguli, Stephen Baccus

Understanding how neural networks transform inputs into outputs is crucial for interpreting and manipulating their behavior. Most existing approaches analyze internal representations by identifying hidden-layer activation patterns correlated with human-interpretable concepts. Here we take a direct approach to examine how hidden neurons act to drive network outputs. We introduce CODEC ($\textbf{Co}$ntribution $\textbf{Dec}$omposition), a method that uses sparse autoencoders to decompose network behavior into sparse motifs of hidden-neuron contributions, revealing causal processes that cannot be determined by analyzing activations alone. Applying CODEC to benchmark image-classification networks, we find that contributions grow in sparsity and dimensionality across layers and, unexpectedly, that they progressively decorrelate positive and negative effects on network outputs. We further show that decomposing contributions into sparse modes enables greater control and interpretation of intermediate layers, supporting both causal manipulations of network output and human-interpretable visualizations of distinct image components that combine to drive that output. Finally, by analyzing state-of-the-art models of neural activity in the vertebrate retina, we demonstrate that CODEC uncovers combinatorial actions of model interneurons and identifies the sources of dynamic receptive fields. Overall, CODEC provides a rich and interpretable framework for understanding how nonlinear computations evolve across hierarchical layers, establishing contribution modes as an informative unit of analysis for mechanistic insights into artificial neural networks.

Applications · Language, Speech and Dialog

Wenbo Shang, Yuxi Sun, Jing Ma, Xin Huang

Humor is a commonly used and intricate human language in daily life. Humor generation, especially in multi-modal scenarios, is a challenging task for large language models (LLMs), which is typically as funny caption generation for images, requiring visual understanding, humor reasoning, creative imagination, and so on. Existing LLM-based approaches rely on reasoning chains or self-improvement, which suffer from limited creativity and interpretability. To address these bottlenecks, we develop a novel LLM-based humor generation mechanism based on a fundamental humor theory, GTVH. To produce funny and script-opposite captions, we introduce a humor-theory-driven multi-role LLM collaboration framework augmented with humor retrieval (HOMER). The framework consists of three LLM-based roles: (1) conflicting-script extractor that grounds humor in key script oppositions, forming the basis of caption generation; (2) retrieval-augmented hierarchical imaginator that identifies key humor targets and expands the creative space of them through diverse associations structured as imagination trees; and (3) caption generator that produces funny and diverse captions conditioned on the obtained knowledge. Extensive experiments on two New Yorker Cartoon benchmarking datasets show that HOMER outperforms state-of-the-art baselines and powerful LLM reasoning strategies on multi-modal humor captioning.

General Machine Learning · Representation Learning

Shujian Gao, Yuan Wang, Chenglong Ma, Xin Gao, Jiangtao Yan, Junzhi Ning, Cheng Tang, Changkai Ji, Huihui Xu, Wei Li 等

Concept Bottleneck Models (CBMs) achieve interpretability by interposing a human-understandable concept layer between perception and label prediction. We first identify that the condition of \textit{many-to-many} mapping is necessary for robust CBMs, a prerequisite that has been largely overlooked in previous approaches. While several recent methods have attempted to establish this relationship, we observe that they suffer from the fundamental issue of \textit{representation collapse}, where visual patch features degenerate into a low-rank subspace during training, severely degrading the quality of learned concept activation vectors, thus hindering both model interpretability and downstream performance. To address these issues, we propose Implicit Vector Quantization (IVQ), a lightweight regularizer that maintains high-rank, diverse representations throughout training. Rather than imposing a hard bottleneck via direct quantization, IVQ learns a codebook prior that anchors semantic information in visual features, allowing it to act as a proxy objective. To further exploit these high-rank concept-aware features, we propose Magnet Attention, which dynamically aggregates patch-level features into visual concept prototypes, explicitly modeling the many-to-many vision–concept correspondence. Extensive experimental results show that our approach effectively prevents representational collapse and achieves state-of-the-art performance on diverse benchmarks. Our experiments further probe the low-rank phenomenon in representational collapse, finding that IVQ mitigates the information bottleneck and yields cross-modal representations with clearer, more interpretable consistency. Code is available at \url{https://github.com/Daryl-GSJ/IVQ-CBM}.

Theory · Interpretability and Visualization

Yoav Gur-Arieh, Mor Geva, Atticus Geiger

A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might represent *Ann loves pie* by binding *Ann* to *pie*, allowing it to later retrieve *Ann* when asked *Who loves pie?* Prior research on short lists of bound entities found strong evidence that LMs implement such retrieval via a **positional mechanism**, where *Ann* is retrieved based on its position in context. In this work, we find that this mechanism generalizes poorly to more complex settings; as the number of bound entities in context increases, the positional mechanism becomes noisy and unreliable in middle positions. To compensate for this, we find that LMs supplement the positional mechanism with a **lexical mechanism** (retrieving *Ann* using its bound counterpart *pie*) and a **reflexive mechanism** (retrieving *Ann* through a direct pointer). Through extensive experiments on nine models and ten binding tasks, we uncover a consistent pattern in how LMs mix these mechanisms to drive model behavior. We leverage these insights to develop a causal model combining all three mechanisms that estimates next token distributions with 95\% agreement. Finally, we show that our model generalizes to substantially longer inputs of open-ended text interleaved with entity groups, further demonstrating the robustness of our findings in more natural settings. Overall, our study establishes a more complete picture of how LMs bind and retrieve entities in-context.

General Machine Learning · Representation Learning

Dominik Sturm, Hiba Bensalem, Ivo Sbalzarini

We introduce spatially informed variational autoencoders (SI-VAE) as self-supervised deep-learning models that use stochastic point processes to predict spatial organization patterns from images. Existing approaches to learning visual representations based on variational autoencoders (VAE) struggle to capture spatial correlations between objects or events, focusing instead on pixel intensities. We address this limitation by incorporating a point-process likelihood, derived from the Papangelou conditional intensity, as a self-supervision target. This results in a hybrid model that learns statistically interpretable representations of spatial localization patterns and enables zero-shot conditional simulation directly from images. Experiments with synthetic images show that SI-VAE improve the classification accuracy of attractive, repulsive, and uncorrelated point patterns from 48% (VAE) to over 80% in the worst case and 90% in the best case, while generalizing to unseen data. We apply SI-VAE to a real-world microscopy data set, demonstrating its use for studying the spatial organization of proteins in human cells and for using the representations in downstream statistical analysis.

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.

Computer Vision · Vision Models & Multimodal

Yicheng Xu, Yue Wu, Jiashuo Yu, Ziang Yan, Tianxiang Jiang, Yinan He, Qingsong Zhao, Kai Chen, Yu Qiao, Limin Wang 等

Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, especially in wet-lab settings. To bridge this gap, we introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos. Curated from peer-reviewed video publications, ExpVid features a new three-level task hierarchy that mirrors the scientific process: (1) Fine-grained Perception of tools, materials, and actions; (2) Procedural Understanding of step order and completeness; and (3) Scientific Reasoning that connects the full experiment to its published conclusions. Our vision-centric annotation pipeline, combining automated generation with multi-disciplinary expert validation, ensures that tasks require visual grounding. We evaluate 20 leading MLLMs on ExpVid and find that while they excel at coarse-grained recognition, they struggle with disambiguating fine details, tracking state changes over time, and linking experimental procedures to scientific outcomes. Our results reveal a notable performance gap between proprietary and open-source models, particularly in high-order reasoning. ExpVid not only provides a diagnostic tool but also charts a roadmap for developing MLLMs capable of becoming trustworthy partners in scientific experimentation.

Computer Vision · Everything Else

Liaoruxing Zhang, Xin Jin, Wenbo Yuan, ChenYu Fan, Song-Chun Zhu

This work proposes a compositional AND–OR template for art and design that encodes the part–relation–geometry organization of images in a structured and interpretable form. Within a maximum-entropy log-linear model, we define a unified consistency score as log-likelihood gain against a reference distribution and decompose it into term-level evidence, enabling an evidence-to-prescription mapping for actionable composition guidance. Learning is performed by a penalized EM-style block-pursuit with sparsity and local mutual exclusivity: object templates are learned first and reused as scene terminals to induce scene templates. A semi-supervised structural expansion, which is triggered by matching gain and structural-consistency thresholds, bootstraps new branches from unlabeled, high-quality images. Evaluations on a curated compositional dataset and AVA/AADB themes show strong agreement with expert paradigms, interpretable parse trees, and competitive performance with deep baselines while exhibiting higher alignment with human ratings. The learned templates also act as lightweight structural conditions to steer AIGC generation and layout design. Overall, the framework delivers a transferable structural prior with favorable data/parameter efficiency and a unified pathway for explainable visual assessment and generation.

Social Aspects · Fairness, Equity, Justice and Safety

Jiaying Wu, Fanxiao Li, Zihang Fu, Min-Yen Kan, Bryan Hooi

The impact of multimodal misinformation arises not only from factual inaccuracies but also from the misleading narratives that creators deliberately embed. Interpreting such creator intent is therefore essential for multimodal misinformation detection (MMD) and effective information governance. To this end, we introduce DeceptionDecoded, a large-scale benchmark of 12,000 image-caption pairs grounded in trustworthy reference articles, created using an intent-guided simulation framework that models both the desired influence and the execution plan of news creators. The dataset captures both misleading and non-misleading cases, spanning manipulations across visual and textual modalities, and supports three intent-centric tasks: (1) misleading intent detection, (2) misleading source attribution, and (3) creator desire inference. We evaluate 14 state-of-the-art vision-language models (VLMs) and find that they struggle with intent reasoning, often relying on shallow cues such as surface-level alignment, stylistic polish, or heuristic authenticity signals. To bridge this, our framework systematically synthesizes data that enables models to learn implication-level intent reasoning. Models trained on DeceptionDecoded demonstrate strong transferability to real-world MMD, validating our framework as both a benchmark to diagnose VLM fragility and a data synthesis engine that provides high-quality, intent-focused resources for enhancing robustness in real-world multimodal misinformation governance.

Theory · Interpretability and Visualization

Itamar Hadad, Guy Katz, Shahaf Bassan

*Automated circuit discovery* is a central tool in mechanistic interpretability for identifying the internal components of neural networks responsible for specific behaviors. While prior methods have made significant progress, they typically depend on heuristics or approximations and do not offer provable guarantees over continuous input domains for the resulting circuits. In this work, we leverage recent advances in neural network verification to propose a suite of automated algorithms that yield circuits with *provable guarantees*. We focus on three types of guarantees: (1) *input domain robustness*, ensuring the circuit agrees with the model across a continuous input region; (2) *robust patching*, certifying circuit alignment under continuous patching perturbations; and (3) *minimality*, formalizing and capturing a wide array of various notions of succinctness. Interestingly, we uncover a diverse set of novel theoretical connections among these three families of guarantees, with critical implications for the convergence of our algorithms. Finally, we conduct experiments with state-of-the-art verifiers on various vision models, showing that our algorithms yield circuits with substantially stronger robustness guarantees than standard circuit discovery methods, establishing a principled foundation for provable circuit discovery.

Theory · Interpretability and Visualization

Scott Viteri, Max Lamparth, Peter Chatain, Clark Barrett

Chain-of-Thought (CoT) reasoning often fails to faithfully reflect a language model's underlying decision process. We address this by introducing a *Markovian* language model framework with an autoencoder-style *reasoning bottleneck*: all information flowing from question to answer must pass through a bounded-length CoT, creating a bandwidth bottleneck analogous to the latent layer of an autoencoder. In practice, the KL penalty toward the pretrained distribution and the inductive biases of gradient descent discourage steganographic encoding, so the model learns to express its reasoning in natural-language steps from which the answer can be derived. We train this system with a GRPO-style policy gradient algorithm using parallel sampling, a frozen baseline CoT$'$, within-batch standardized advantages, and actor-reward (chain-rule) gradients. On QA tasks, Markovian training recovers most of the gains of a Non-Markovian GRPO variant while forcing the model to answer from the CoT alone (e.g., GSM8K: 19.6\% $\to$ 57.1\%; ARC-Challenge: 36.1\% $\to$ 79.9\%; on average within $\approx$3--4 pp of a Non-Markovian variant). Perturbation analyses across types and severities show that Markovian models incur systematically larger log-probability drops under CoT corruption than matched Non-Markovian baselines, indicating stronger causal reliance on the CoT. Cross-model evaluation confirms that learned CoTs generalize across architectures, suggesting they encode transferable reasoning steps rather than model-specific artifacts.

Applications · Neuroscience, Cognitive Science

Lorenzo Tausani, Paolo Muratore, Morgan B Talbot, Giacomo Amerio, Gabriel Kreiman, Davide Zoccolan

Uncovering which feature combinations are encoded by visual units is critical to understanding how images are transformed into representations that support recognition. While existing feature visualization approaches typically infer a unit's most exciting images, this is insufficient to reveal the manifold of transformations under which responses remain invariant, which is critical to generalization in vision. Here we introduce Stretch-and-Squeeze (SnS), an unbiased, model-agnostic, and gradient-free framework to systematically characterize a unit’s maximally invariant stimuli, and its vulnerability to adversarial perturbations, in both biological and artificial visual systems. SnS frames these transformations as bi-objective optimization problems. To probe invariance, SnS seeks image perturbations that maximally alter (stretch) the representation of a reference stimulus in a given processing stage while preserving unit activation downstream (squeeze). To probe adversarial sensitivity, stretching and squeezing are reversed to maximally perturb unit activation while minimizing changes to the upstream representation. Applied to CNNs, SnS revealed invariant transformations that were farther from a reference image in pixel-space than those produced by affine transformations, while more strongly preserving the target unit's response. The discovered invariant images differed depending on the stage of the image representation used for optimization: pixel-level changes primarily affected luminance and contrast, while stretching mid- and late-layer representations mainly altered texture and pose. By measuring how well the hierarchical invariant images obtained for $L_2$-robust (i.e., adversarially trained) networks were classified by humans and other observer networks, we discovered a substantial drop in their interpretability when the representation was stretched in deep layers, while the opposite trend was found for standard (i.e., not robustified) models. This indicates that $L_2$ adversarial training fails to increase the interpretability of high-level invariances, despite good perceptual alignment between humans and robustified models at the pixel level. This demonstrates how SnS can be used as a powerful new tool to measure the alignment between artificial and biological vision.

Theory · Interpretability and Visualization

Clément Cornet, Romaric Besançon, Hervé Le Borgne

We propose an alternative to sparse autoencoders (SAEs) as a simple and effective unsupervised method for extracting interpretable concepts from neural networks. The core idea is to cluster differences in activations, which we formally justify within a discriminant analysis framework. To enhance the diversity of extracted concepts, we refine the approach by weighting the clustering using the skewness of activations. The method aligns with Deleuze's modern view of concepts as differences. We evaluate the approach across five models and three modalities (vision, language, and audio), measuring concept quality, diversity, and consistency. Our results show that the proposed method achieves concept quality surpassing prior unsupervised SAE variants while approaching supervised baselines, and that the extracted concepts enable steering of a model’s inner representations, demonstrating their causal influence on downstream behavior.

Xilin Wei, Xiaoran Liu, Yuhang Zang, Xiaoyi Dong, Yuhang Cao, Jiaqi Wang, Xipeng Qiu, Dahua Lin

Implicit Chain-of-Thought (CoT) methods offer a token-efficient alternative to explicit CoT reasoning in Large Language Models (LLMs), but a persistent performance gap has limited their adoption. We identify a core latent instability issue when scaling the computational budget of implicit CoT: as the number of reasoning tokens increases, training often becomes unstable and collapses. Our analysis shows that this instability arises from latent representations becoming homogeneous and losing semantic diversity, caused by insufficient step-level supervision in current implicit CoT methods. To address this, we propose SIM-CoT, a plug-and-play training module that introduces step-level supervision to stabilize and enrich the latent reasoning space. SIM-CoT employs an auxiliary decoder during training to align each implicit token with its corresponding explicit reasoning step, ensuring latent states capture distinct and meaningful information. The auxiliary decoder is removed at inference, preserving the efficiency of implicit CoT with no added overhead. It also provides interpretability by projecting each latent token onto an explicit reasoning vocabulary, enabling per-step visualization and diagnosis. SIM-CoT significantly improves both in-domain accuracy and out-of-domain stability of implicit CoT methods, boosting Coconut by +8.2\% on GPT-2 and CODI by +3.0\% on LLaMA-3.1 8B. It further surpasses the explicit CoT baseline on GPT-2 by 2.1\% with 2.3$\times$ greater token efficiency, while closing the performance gap on larger models like LLaMA-3.1 8B.

General Machine Learning · Representation Learning

Gong Zhiren, Chao Yang, Wendi Ren, Shuang Li

Humans navigate daily life by combining two modes of behavior: deliberate planning in novel situations and fast, automatic responses in familiar ones. Modeling human decision-making therefore requires capturing how people switch between these modes. We present a framework for learning human habits with rule-guided active inference, extending the view of the brain as a prediction machine that minimizes mismatches between expectations and observations, and computationally modeling of human(-like) behavior and habits. In our approach, habits emerge as symbolic rules that serve as compact, interpretable shortcuts for action. To learn these rules alongside the human models, we design a biologically inspired wake--sleep algorithm. In the wake phase, the agent engages in active inference on real trajectories: reconstructing states, updating beliefs, and harvesting candidate rules that reliably reduce free energy. In the sleep phase, the agent performs generative replay with its world model, refining parameters and consolidating or pruning rules by minimizing joint free energy. This alternating rule–model consolidation lets the agent build a reusable habit library while preserving the flexibility to plan. Experiments on basketball player movements, car-following behavior, medical diagnosis, and visual game strategy demonstrate that our framework improves predictive accuracy and efficiency compared to logic-based, deep learning, LLM-based, model-based RL, and prior active inference baselines, while producing interpretable rules that mirror human-like habits.

Theory · Interpretability and Visualization

Vishal Pramanik, Maisha Maliha, Nathaniel Bastian, Sumit Jha

Attribution methods seek to explain language model predictions by quantifying the contribution of input tokens to generated outputs. However, most existing techniques are designed for encoder-based architectures and rely on linear approximations that fail to capture the causal and semantic complexities of autoregressive generation in decoder-only models. To address these limitations, we propose **Hessian-Enhanced Token Attribution (HETA)**, a novel attribution framework tailored for decoder-only language models. HETA combines three complementary components: a semantic transition vector that captures token-to-token influence across layers, Hessian-based sensitivity scores that model second-order effects, and KL divergence to measure information loss when tokens are masked. This unified design produces context-aware, causally faithful, and semantically grounded attributions. Additionally, we introduce a **curated benchmark dataset** for systematically evaluating attribution quality in generative settings. Empirical evaluations across multiple models and datasets demonstrate that HETA consistently outperforms existing methods in attribution faithfulness and alignment with human annotations, establishing a new standard for interpretability in autoregressive language models.