More Like this

1. SPEX: scaling feature interaction explanations for LLMs

   Kang, Justin; Butler, Landon; Agarwal, Abhineet; Erginbas, Yigit; Pedarsani, Ramtin; Yu, Bin; Ramchandran, Kannan (July 2025, International Conference on Machine Learning)

   Large language models (LLMs) have revolutionized machine learning due to their ability to capture complex interactions between input features. Popular post-hoc explanation methods like SHAP provide marginal feature attributions, while their extensions to interaction importances only scale to small input lengths (≈ 20). We propose Spectral Explainer (SPEX), a model-agnostic interaction attribution algorithm that efficiently scales to large input lengths (≈ 1000). SPEX exploits underlying natural sparsity among interactions—common in realworld data—and applies a sparse Fourier transform using a channel decoding algorithm to efficiently identify important interactions. We perform experiments across three difficult long-context datasets that require LLMs to utilize interactions between inputs to complete the task. For large inputs, SPEX outperforms marginal attribution methods by up to 20% in terms of faithfully reconstructing LLM outputs. Further, SPEX successfully identifies key features and interactions that strongly influence model output. For one of our datasets, HotpotQA, SPEX provides interactions that align with human annotations. Finally, we use our model-agnostic approach to generate explanations to demonstrate abstract reasoning in closed-source LLMs (GPT-4o mini) and compositional reasoning in vision-language models. 

   more » « less
2. K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Prediction

   https://doi.org/10.1145/3711896.3737011  

   Abdullahi, Tassallah; Gemou, Ioanna; Nayak, Nihal V; Murtaza, Ghulam; Bach, Stephen H; Eickhoff, Carsten; Singh, Ritambhara (August 2025, KDD '25: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining)

   Biomedical knowledge graphs (KGs) encode rich, structured information critical for drug discovery tasks, but extracting meaningful insights from large-scale KGs remains challenging due to their complex structure. Existing biomedical subgraph retrieval methods are tailored for graph neural networks (GNNs), limiting compatibility with other paradigms, including large language models (LLMs). We introduce K-Paths, a model-agnostic retrieval framework that extracts structured, diverse, and biologically meaningful multi-hop paths from dense biomedical KGs. These paths enable prediction of unobserved drug-drug and drug-disease interactions, including those involving entities not seen during training, thus supporting inductive reasoning. K-Paths is training-free and employs a diversity-aware adaptation of Yen's algorithm to extract the K shortest loopless paths between entities in a query, prioritizing biologically relevant and relationally diverse connections. These paths serve as concise, interpretable reasoning chains that can be directly integrated with LLMs or GNNs to improve generalization, accuracy, and enable explainable inference. Experiments on benchmark datasets show that K-Paths improves zero-shot reasoning across state-of-the-art LLMs. For instance, Tx-Gemma 27B improves by 19.8 and 4.0 F1 points on interaction severity prediction and drug repurposing tasks, respectively. Llama 70B achieves gains of 8.5 and 6.2 points on the same tasks. K-Paths also boosts the training efficiency of EmerGNN, a state-of-the-art GNN, by reducing the KG size by 90% while maintaining predictive performance. Beyond efficiency, K-Paths bridges the gap between KGs and LLMs, enabling scalable and explainable LLM-augmented scientific discovery. We release our code and the retrieved paths as a benchmark for inductive reasoning. 

   more » « less
3. MASE: Interpretable NLP Models via Model-Agnostic Saliency Estimation

   https://doi.org/10.1109/BigData66926.2025.11402020  

   Yang, Zhou; Luo, Shunyan; Zhu, Jiazhen; Jin, Fang (December 2025, IEEE)

   Deep neural networks (DNNs) have made significant strides in Natural Language Processing (NLP), yet their interpretability remains elusive, particularly when evaluating their intricate decision-making processes. Traditional methods often rely on post-hoc interpretations, such as saliency maps or feature visualization, which might not be directly applicable to the discrete nature of word data in NLP. Addressing this, we introduce the Model-agnostic Saliency Estimation (MASE) framework. MASE offers local explanations for text-based predictive models without necessitating in-depth knowledge of a model’s internal architecture. By leveraging Normalized Linear Gaussian Perturbations (NLGP) on the embedding layer instead of raw word inputs, MASE efficiently estimates input saliency. Our results indicate MASE’s superiority over other model agnostic interpretation methods, especially in terms of Delta Accuracy, positioning it as a promising tool for elucidating the operations of text-based models in NLP. 

   more » « less
4. Reductive Analysis with Compiler-Guided Large Language Models for Input-Centric Code Optimizations

   https://doi.org/10.1145/3729282  

   Wang, Xiangwei; Hui, Xinning; Liao, Chunhua; Shen, Xipeng (June 2025, Proceedings of the ACM on Programming Languages)

   Input-centric program optimization aims to optimize code by considering the relations between program inputs and program behaviors. Despite its promise, a long-standing barrier for its adoption is the difficulty of automatically identifying critical features of complex inputs. This paper introduces a novel technique,reductive analysis through compiler-guided Large Language Models (LLMs), to solve the problem through a synergy between compilers and LLMs. It uses a reductive approach to overcome the scalability and other limitations of LLMs in program code analysis. The solution, for the first time, automates the identification of critical input features without heavy instrumentation or profiling, cutting the time needed for input identification by 44× (or 450× for local LLMs), reduced from 9.6 hours to 13 minutes (with remote LLMs) or 77 seconds (with local LLMs) on average, making input characterization possible to be integrated into the workflow of program compilations. Optimizations on those identified input features show similar or even better results than those identified by previous profiling-based methods, leading to optimizations that yield 92.6% accuracy in selecting the appropriate adaptive OpenMP parallelization decisions, and 20–30% performance improvement of serverless computing while reducing resource usage by 50–60%. 

   more » « less
5. Can LLMs Be Effective Sensor Processing Copilots?

   https://doi.org/10.1109/JIOT.2026.3664751  

   Quan, Pengrui; Ouyang, Xiaomin; Jeyakumar, Jeya Vikranth; Wang, Ziqi; Xing, Yang; Srivastava, Mani (May 2026, IEEE Internet of Things Journal)

   Effective sensor data processing is critical for cyber-physical and Internet of Things (IoT) systems, but often requires specialized expertise. While large language models (LLMs) show promise as autonomous copilots for sensor processing, their capabilities remain underexplored. We introduce SensorBench, the first comprehensive benchmark for evaluating LLMs across diverse real-world sensor datasets and tasks. SensorBench evaluates three paradigms for leveraging LLMs in sensing tasks: tool-augmented coding (TAC), standalone coding (SAC), and direct answer (DA). We evaluate 8 leading LLM variants, including 2 large reasoning models (LRMs) and 2 domain-specific LLMs, providing a structured reference for absolute performance, latency, and resource requirements. Our analysis reveals that: 1) TAC significantly outperforms SAC and DA; 2) LLMs excel at simple tasks but consistently underperform domain experts on compositional tasks requiring parameter tuning and multistep reasoning; and 3) the reasoning mechanism introduced in LRMs does not yield substantial performance gains. To improve the performance, we explore four prompting strategies and fine-tuning approaches (using our newly released sensor-processing corpus). The results show that self-verification prompting proves most effective, outperforming other methods simultaneously in 48% of tasks, while fine-tuning yields marginal gains. Our analysis suggests that more sophisticated interaction frameworks, such as signal-level self-verification, may bridge the gap to human expert-level performance. This benchmark provides a foundation for evaluating and improving LLMs in sensing applications https://github.com/nesl/LLM_sensor_processing 

   more » « less