English
Related papers

Related papers: Logic Traps in Evaluating Attribution Scores

200 papers

This study investigates the attribution patterns underlying Chain-of-Thought (CoT) reasoning in multilingual LLMs. While prior works demonstrate the role of CoT prompting in improving task performance, there are concerns regarding the…

Computation and Language · Computer Science 2025-11-21 Jeremias Ferrao , Ezgi Basar , Khondoker Ittehadul Islam , Mahrokh Hassani

Explicit reasoning models are trained to produce intermediate reasoning traces before final answers, but downstream fine-tuning is often performed on ordinary instruction-response data that contains no such traces. We show that this…

Machine Learning · Computer Science 2026-05-21 Lukas Twist , Helen Yannakoudakis , Jie M. Zhang

Recent generations of language models have introduced Large Reasoning Models (LRMs) that generate detailed thinking processes before providing answers. While these models demonstrate improved performance on reasoning benchmarks, their…

Artificial Intelligence · Computer Science 2025-11-21 Parshin Shojaee , Iman Mirzadeh , Keivan Alizadeh , Maxwell Horton , Samy Bengio , Mehrdad Farajtabar

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Sukrut Rao , Moritz Böhle , Bernt Schiele

We analyze state-of-the-art deep learning models for three tasks: question answering on (1) images, (2) tables, and (3) passages of text. Using the notion of \emph{attribution} (word importance), we find that these deep networks often…

Computation and Language · Computer Science 2018-05-16 Pramod Kaushik Mudrakarta , Ankur Taly , Mukund Sundararajan , Kedar Dhamdhere

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input hyperparameters which are often randomly set or empirically…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Naman Bansal , Chirag Agarwal , Anh Nguyen

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Sukrut Rao , Moritz Böhle , Bernt Schiele

Ensuring the trustworthiness and interpretability of machine learning models is critical to their deployment in real-world applications. Feature attribution methods have gained significant attention, which provide local explanations of…

Machine Learning · Computer Science 2023-09-20 Md Abdul Kadir , Gowtham Krishna Addluri , Daniel Sonntag

Step-by-step reasoning is widely used to enhance the reasoning ability of large language models (LLMs) in complex problems. Evaluating the quality of reasoning traces is crucial for understanding and improving LLM reasoning. However,…

Computation and Language · Computer Science 2025-09-23 Jinu Lee , Julia Hockenmaier

While SHAP (SHapley Additive exPlanations) and other feature attribution methods are commonly employed to explain model predictions, their application within information retrieval (IR), particularly for complex outputs such as ranked lists,…

Information Retrieval · Computer Science 2025-05-01 Maria Heuss , Maarten de Rijke , Avishek Anand

We study how well large language models (LLMs) explain their generations through rationales -- a set of tokens extracted from the input text that reflect the decision-making process of LLMs. Specifically, we systematically study rationales…

Computation and Language · Computer Science 2024-10-23 Mohsen Fayyaz , Fan Yin , Jiao Sun , Nanyun Peng

For machine learning models to be reliable and trustworthy, their decisions must be interpretable. As these models find increasing use in safety-critical applications, it is important that not just the model predictions but also their…

Machine Learning · Computer Science 2023-12-19 Sandesh Kamath , Sankalp Mittal , Amit Deshpande , Vineeth N Balasubramanian

Large language models (LLMs) are increasingly used as raters for evaluation tasks. However, their reliability is often limited for subjective tasks, when human judgments involve subtle reasoning beyond annotation labels. Thinking traces,…

Artificial Intelligence · Computer Science 2026-02-23 Xingjian Zhang , Tianhong Gao , Suliang Jin , Tianhao Wang , Teng Ye , Eytan Adar , Qiaozhu Mei

While diffusion models excel at image generation, their growing adoption raises critical concerns about copyright issues and model transparency. Existing attribution methods identify training examples influencing an entire image, but fall…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Yonghyun Park , Chieh-Hsin Lai , Satoshi Hayakawa , Yuhta Takida , Naoki Murata , Wei-Hsiang Liao , Woosung Choi , Kin Wai Cheuk , Junghyun Koo , Yuki Mitsufuji

Attribution methods reveal which input features a neural network uses for a prediction, adding transparency to their decisions. A common problem is that these attributions seem unspecific, highlighting both important and irrelevant…

Computer Vision and Pattern Recognition · Computer Science 2026-02-06 Nils Philipp Walter , Jilles Vreeken , Jonas Fischer

The recent advancements in Deep Learning models and techniques have led to significant strides in performance across diverse tasks and modalities. However, while the overall capabilities of models show promising growth, our understanding of…

Artificial Intelligence · Computer Science 2025-04-04 Erik Arakelyan

Learning-to-rank (LTR) is a class of supervised learning techniques that apply to ranking problems dealing with a large number of features. The popularity and widespread application of LTR models in prioritizing information in a variety of…

Machine Learning · Computer Science 2020-05-19 Jaspreet Singh , Zhenye Wang , Megha Khosla , Avishek Anand

Large Language Models (LLMs)-based question answering (QA) systems play a critical role in modern AI, demonstrating strong performance across various tasks. However, LLM-generated responses often suffer from hallucinations, unfaithful…

Computation and Language · Computer Science 2026-01-29 Yuqing Zhao , Ziyao Liu , Yongsen Zheng , Kwok-Yan Lam

There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…

Computation and Language · Computer Science 2023-12-11 Simon Lermen , Ondřej Kvapil

Multi-round incomplete information tasks are crucial for evaluating the lateral thinking capabilities of large language models (LLMs). Currently, research primarily relies on multiple benchmarks and automated evaluation metrics to assess…

Computation and Language · Computer Science 2025-06-02 Wenhan Dong , Tianyi Hu , Jingyi Zheng , Zhen Sun , Yuemeng Zhao , Yule Liu , Xinlei He , Xinyi Huang