English
Related papers

Related papers: Rethinking Explanation Evaluation under the Retrai…

200 papers

Good quality explanations strengthen the understanding of language models and data. Feature attribution methods, such as Integrated Gradient, are a type of post-hoc explainer that can provide token-level insights. However, explanations on…

Computation and Language · Computer Science 2026-04-21 Jonathan Kamp , Roos Bakker , Dominique Blok

The growing need for trustworthy machine learning has led to the blossom of interpretability research. Numerous explanation methods have been developed to serve this purpose. However, these methods are deficiently and inappropriately…

Machine Learning · Computer Science 2022-03-29 Yipei Wang , Xiaoqian Wang

The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\pi$. This problem is difficult, for several reasons. First of all, there are typically multiple reward functions which are compatible with a…

Machine Learning · Computer Science 2024-11-26 Joar Skalse , Alessandro Abate

Many methods now exist for conditioning model outputs on task instructions, retrieved documents, and user-provided explanations and feedback. Rather than relying solely on examples of task inputs and outputs, these approaches use valuable…

Computation and Language · Computer Science 2021-02-12 Peter Hase , Mohit Bansal

The goal of data attribution is to trace the model's predictions through the learning algorithm and back to its training data. thereby identifying the most influential training samples and understanding how the model's behavior leads to…

Machine Learning · Computer Science 2025-08-12 Hongbo Zhu , Angelo Cangelosi

Feature based explanations, that provide importance of each feature towards the model prediction, is arguably one of the most intuitive ways to explain a model. In this paper, we establish a novel set of evaluation criteria for such feature…

Machine Learning · Computer Science 2021-04-12 Cheng-Yu Hsieh , Chih-Kuan Yeh , Xuanqing Liu , Pradeep Ravikumar , Seungyeon Kim , Sanjiv Kumar , Cho-Jui Hsieh

This paper introduces an explanation framework designed to enhance the quality of rules in knowledge-based reasoning systems based on dataset-driven insights. The traditional method for rule induction from data typically requires…

Artificial Intelligence · Computer Science 2025-02-04 Oshani Seneviratne , Brendan Capuzzo , William Van Woensel

Recommender systems are central to digital platforms, yet they face a fundamental trade-off between accuracy and explainability. Black-box models achieve strong performance but lack interpretability needed for trust and adoption. Existing…

Information Retrieval · Computer Science 2026-05-05 Yuyan Wang , Pan Li , Minmin Chen

The reasoning abilities of large language models (LLMs) have improved with chain-of-thought (CoT) prompting, allowing models to solve complex tasks stepwise. However, training CoT capabilities requires detailed reasoning data, which is…

Artificial Intelligence · Computer Science 2025-04-11 Fu-Chieh Chang , Yu-Ting Lee , Hui-Ying Shih , Yi Hsuan Tseng , Pei-Yuan Wu

Post-hoc importance attribution methods are a popular tool for "explaining" Deep Neural Networks (DNNs) and are inherently based on the assumption that the explanations can be applied independently of how the models were trained.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Siddhartha Gairola , Moritz Böhle , Francesco Locatello , Bernt Schiele

Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing…

Machine Learning · Computer Science 2024-04-02 Wenhao Lu , Xufeng Zhao , Thilo Fryen , Jae Hee Lee , Mengdi Li , Sven Magg , Stefan Wermter

Instruction tuning increasingly relies on LLM-based prompt refinement, where prompts in the training corpus are selectively rewritten by an external refiner to improve clarity and instruction alignment. This motivates an instance-level…

Machine Learning · Computer Science 2026-01-06 Bo Yin , Qi Li , Runpeng Yu , Xinchao Wang

The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on…

Machine Learning · Computer Science 2026-04-20 You Qin , Linqing Wang , Hao Fei , Roger Zimmermann , Liefeng Bo , Qinglin Lu , Chunyu Wang

Recent curriculum techniques in the post-training stage of LLMs have been empirically observed to outperform non-curriculum approaches in improving reasoning performance, yet a principled understanding of their effectiveness and limitations…

Machine Learning · Computer Science 2026-05-05 Dake Bu , Wei Huang , Andi Han , Atsushi Nitanda , Hau-San Wong , Qingfu Zhang , Taiji Suzuki

While reasoning models (e.g., DeepSeek R1) trained with reinforcement learning (RL), excel in textual reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric reasoning, concise computation, or complex…

Computation and Language · Computer Science 2025-04-18 Jiazhan Feng , Shijue Huang , Xingwei Qu , Ge Zhang , Yujia Qin , Baoquan Zhong , Chengquan Jiang , Jinxin Chi , Wanjun Zhong

As machine learning models are increasingly considered for high-stakes domains, effective explanation methods are crucial to ensure that their prediction strategies are transparent to the user. Over the years, numerous metrics have been…

Machine Learning · Computer Science 2025-04-14 Johannes Maeß , Grégoire Montavon , Shinichi Nakajima , Klaus-Robert Müller , Thomas Schnake

Artificial intelligence (AI) has been embedded into many aspects of people's daily lives and it has become normal for people to have AI make decisions for them. Reinforcement learning (RL) models increase the space of solvable problems with…

Artificial Intelligence · Computer Science 2022-03-23 Agneza Krajna , Mario Brcic , Tomislav Lipic , Juraj Doncevic

Experience replay serves as a key component in the success of online reinforcement learning (RL). Prioritized experience replay (PER) reweights experiences by the temporal difference (TD) error empirically enhancing the performance.…

Machine Learning · Computer Science 2024-09-20 Changling Li , Zhang-Wei Hong , Pulkit Agrawal , Divyansh Garg , Joni Pajarinen

We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as…

Machine Learning · Computer Science 2025-03-05 Johannes Schneider , Michalis Vlachos

Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning…