Explainable Artificial Intelligence (XAI)

Derniers papiers

• Distilling Lightweight Domain Experts from Large ML Models by Identifying Relevant Subspaces

  Pattarawat Chormai, Ali Hashemi, Klaus-Robert M\"uller, Gr\'egoire Montavon · 12 janvier 2026

  Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address the scenario in which only a few classes and their associated …

• Efficient Inference for Noisy LLM-as-a-Judge Evaluation

  Yiqun T Chen, Sizhu Lu, Sijia Li, Moran Guo, Shengyi Li · 12 janvier 2026

  Large language models (LLMs) are increasingly used as automatic evaluators of generative AI outputs, a paradigm often referred to as "LLM-as-a-judge." In practice, LLM judges are imperfect predictions for the underlying truth and can exhibit systematic, non-random errors. Two main approaches have re…

• TDHook: A Lightweight Framework for Interpretability

  Yoann Poupart · 12 janvier 2026

  Interpretability of Deep Neural Networks (DNNs) is a growing field driven by the study of vision and language models. Yet, some use cases, like image captioning, or domains like Deep Reinforcement Learning (DRL), require complex modelling, with multiple inputs and outputs or use composable and separ…

• ART: Adaptive Reasoning Trees for Explainable Claim Verification

  Sahil Wadhwa, Himanshu Kumar, Guanqun Yang, Abbaas Alif Mohamed Nishar, Pranab Mohanty, Swapnil Shinde, Yue Wu · 12 janvier 2026

  Large Language Models (LLMs) are powerful candidates for complex decision-making, leveraging vast encoded knowledge and remarkable zero-shot abilities. However, their adoption in high-stakes environments is hindered by their opacity; their outputs lack faithful explanations and cannot be effectively…

• Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs

  Alireza Dehghanpour Farashah, Aditi Khandelwal, Marylou Fauchard, Zhuan Shi, Negar Rostamzadeh, Golnoosh Farnadi · 12 janvier 2026

  As multilingual large language models become more widely used, ensuring their safety and fairness across diverse linguistic contexts presents unique challenges. While existing research on machine unlearning has primarily focused on monolingual settings, typically English, multilingual environments i…

• Buffered AUC maximization for scoring systems via mixed-integer optimization

  Moe Shiina, Shunnosuke Ikeda, Yuichi Takano · 12 janvier 2026

  A scoring system is a linear classifier composed of a small number of explanatory variables, each assigned a small integer coefficient. This system is highly interpretable and allows predictions to be made with simple manual calculations without the need for a calculator. Several previous studies ha…

• Explainable AI: Learning from the Learners

  Ricardo Vinuesa, Steven L. Brunton, Gianmarco Mengaldo · 12 janvier 2026

  Artificial intelligence now outperforms humans in several scientific and engineering tasks, yet its internal representations often remain opaque. In this Perspective, we argue that explainable artificial intelligence (XAI), combined with causal reasoning, enables {\it learning from the learners}. Fo…

• Explainable AI needs formalization

  Stefan Haufe, Rick Wilming, Benedict Clark, Rustam Zhumagambetov, Ahc\`ene Boubekki, J\"org Martin, Danny Panknin · 12 janvier 2026

  The field of "explainable artificial intelligence" (XAI) seemingly addresses the desire that decisions of machine learning systems should be human-understandable. However, in its current state, XAI itself needs scrutiny. Popular methods cannot reliably answer relevant questions about ML models, thei…

• Mechanistic Indicators of Understanding in Large Language Models

  Pierre Beckmann, Matthieu Queloz · 12 janvier 2026

  Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of LLMs, render this picture increasingly untenable--but only once…

• ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging

  Junyao Yang, Chen Qian, Dongrui Liu, Wen Shen, Yong Liu, Jing Shao · 12 janvier 2026

  Large Reasoning Models (LRMs) with long chain-of-thought reasoning have recently achieved remarkable success. Yet, equipping domain-specialized models with such reasoning capabilities, referred to as "Reasoning + X", remains a significant challenge. While model merging offers a promising training-fr…

• The Price of Thought: A Multilingual Analysis of Reasoning, Performance, and Cost of Negotiation in Large Language Models

  Sherzod Hakimov, Roland Bernard, Tim Leiber, Karl Osswald, Kristina Richert, Ruilin Yang, Raffaella Bernardi, David Schlangen · 12 janvier 2026

  Negotiation is a fundamental challenge for AI agents, as it requires an ability to reason strategically, model opponents, and balance cooperation with competition. We present the first comprehensive study that systematically evaluates how explicit reasoning training affects the negotiation abilities…

• Can We Predict Before Executing Machine Learning Agents?

  Jingsheng Zheng, Jintian Zhang, Yujie Luo, Yuren Mao, Yunjun Gao, Lun Du, Huajun Chen, Ningyu Zhang · 12 janvier 2026

  Autonomous machine learning agents have revolutionized scientific discovery, yet they remain constrained by a Generate-Execute-Feedback paradigm. Previous approaches suffer from a severe Execution Bottleneck, as hypothesis evaluation relies strictly on expensive physical execution. To bypass these p…

• Reward Shaping to Mitigate Reward Hacking in RLHF

  Jiayi Fu, Xuandong Zhao, Chengyuan Yao, Heng Wang, Qi Han, Yanghua Xiao · 9 janvier 2026

  Reinforcement Learning from Human Feedback (RLHF) is essential for aligning large language models (LLMs) with human values. However, RLHF is susceptible to \emph{reward hacking}, where the agent exploits flaws in the reward function rather than learning the intended behavior, thus degrading alignmen…

• When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models

  Yingzhi Mao, Chunkang Zhang, Junxiang Wang, Xinyan Guan, Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun · 9 janvier 2026

  Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harmful content generation. Existing methods often apply coarse-grained constraints over the entire reasoning trajectories, which can undermine reasoning ca…

• DeepHalo: A Neural Choice Model with Controllable Context Effects

  Shuhan Zhang, Zhi Wang, Rui Gao, Shuang Li · 9 janvier 2026

  Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of t…

• Learning to Reason: Temporal Saliency Distillation for Interpretable Knowledge Transfer

  Nilushika Udayangani Hewa Dehigahawattage, Kishor Nandakishor, Marimuthu Palaniswami · 9 janvier 2026

  Knowledge distillation has proven effective for model compression by transferring knowledge from a larger network called the teacher to a smaller network called the student. Current knowledge distillation in time series is predominantly based on logit and feature aligning techniques originally devel…

• On the Definition and Detection of Cherry-Picking in Counterfactual Explanations

  James Hinns, Sofie Goethals, Stephan Van der Veeken, Theodoros Evgeniou, David Martens · 9 janvier 2026

  Counterfactual explanations are widely used to communicate how inputs must change for a model to alter its prediction. For a single instance, many valid counterfactuals can exist, which leaves open the possibility for an explanation provider to cherry-pick explanations that better suit a narrative o…

• LLMs for Explainable Business Decision-Making: A Reinforcement Learning Fine-Tuning Approach

  Xiang Cheng, Wen Wang, Anindya Ghose · 9 janvier 2026

  Artificial Intelligence (AI) models increasingly drive high-stakes consumer interactions, yet their decision logic often remains opaque. Prevailing explainable AI techniques rely on post hoc numerical feature attributions, which fail to provide coherent narratives behind model decisions. Large langu…

• Chain-of-Sanitized-Thoughts: Plugging PII Leakage in CoT of Large Reasoning Models

  Arghyadeep Das, Sai Sreenivas Chintha, Rishiraj Girmal, Kinjal Pandey, Sharvi Endait · 9 janvier 2026

  Large Reasoning Models (LRMs) improve performance, reliability, and interpretability by generating explicit chain-of-thought (CoT) reasoning, but this transparency introduces a serious privacy risk: intermediate reasoning often leaks personally identifiable information (PII) even when final answers …

• GlimpRouter: Efficient Collaborative Inference by Glimpsing One Token of Thoughts

  Wenhao Zeng, Xuteng Zhang, Yuling Shi, Chao Hu, Yuting Chen, Beijun Shen, Xiaodong Gu · 9 janvier 2026

  Large Reasoning Models (LRMs) achieve remarkable performance by explicitly generating multi-step chains of thought, but this capability incurs substantial inference latency and computational cost. Collaborative inference offers a promising solution by selectively allocating work between lightweight …

• Generative AI for Social Impact

  Lingkai Kong, Cheol Woo Kim, Davin Choo, Milind Tambe · 9 janvier 2026

  AI for Social Impact (AI4SI) has achieved compelling results in public health, conservation, and security, yet scaling these successes remains difficult due to a persistent deployment bottleneck. We characterize this bottleneck through three coupled gaps: observational scarcity resulting from limite…

• Aligned explanations in neural networks

  Corentin Lobet, Francesca Chiaromonte · 9 janvier 2026

  Feature attribution is the dominant paradigm for explaining deep neural networks. However, most existing methods only loosely reflect the model's prediction-making process, thereby merely white-painting the black box. We argue that explanatory alignment is a key aspect of trustworthiness in predicti…

• AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?

  Henan Sun, Kaichi Yu, Yuyao Wang, Bowen Liu, Xunkai Li, Rong-Hua Li, Nuo Chen, Jia Li · 9 janvier 2026

  Reasoning ability has become a central focus in the advancement of Large Reasoning Models (LRMs). Although notable progress has been achieved on several reasoning benchmarks such as MATH500 and LiveCodeBench, existing benchmarks for algorithmic reasoning remain limited, failing to answer a critical …

• Agent-as-a-Judge

  Runyang You, Hongru Cai, Caiqi Zhang, Qiancheng Xu, Meng Liu, Tiezheng Yu, Yongqi Li, Wenjie Li · 9 janvier 2026

  LLM-as-a-Judge has revolutionized AI evaluation by leveraging large language models for scalable assessments. However, as evaluands become increasingly complex, specialized, and multi-step, the reliability of LLM-as-a-Judge has become constrained by inherent biases, shallow single-pass reasoning, an…

• From Actions to Words: Towards Abstractive-Textual Policy Summarization in RL

  Sahar Admoni, Assaf Hallak, Yftah Ziser, Omer Ben-Porat, Ofra Amir · 9 janvier 2026

  Explaining reinforcement learning agents is challenging because policies emerge from complex reward structures and neural representations that are difficult for humans to interpret. Existing approaches often rely on curated demonstrations that expose local behaviors but provide limited insight into …