English
Related papers

Related papers: How does GPT-2 Predict Acronyms? Extracting and Un…

200 papers

As the use of deep learning techniques has grown across various fields over the past decade, complaints about the opaqueness of the black-box models have increased, resulting in an increased focus on transparency in deep learning models.…

Computation and Language · Computer Science 2024-03-19 Siwen Luo , Hamish Ivison , Caren Han , Josiah Poon

As large language models become increasingly capable, there is growing concern that they may develop reasoning processes that are encoded or hidden from human oversight. To investigate whether current interpretability techniques can…

Artificial Intelligence · Computer Science 2025-12-09 Ching Fang , Samuel Marks

As artificial intelligence is increasingly affecting all parts of society and life, there is growing recognition that human interpretability of machine learning models is important. It is often argued that accuracy or other similar…

Machine Learning · Statistics 2018-06-27 Kush R. Varshney , Prashant Khanduri , Pranay Sharma , Shan Zhang , Pramod K. Varshney

Predictive models are omnipresent in automated and assisted decision making scenarios. But for the most part they are used as black boxes which output a prediction without understanding partially or even completely how different features…

Information Retrieval · Computer Science 2018-07-02 Jaspreet Singh , Avishek Anand

Large language models (LLMs) sometimes fail to respond appropriately to deterministic tasks -- such as counting or forming acronyms -- because the implicit prior distribution they have learned over sequences of tokens influences their…

Computation and Language · Computer Science 2025-04-18 Liyi Zhang , Veniamin Veselovsky , R. Thomas McCoy , Thomas L. Griffiths

Mechanistic interpretability focuses on reverse engineering the internal mechanisms learned by neural networks. We extend our focus and propose to mechanistically forward engineer using our framework based on Concept Bottleneck Models. In…

Machine Learning · Computer Science 2025-12-01 Angela van Sprang , Erman Acar , Willem Zuidema

Neural networks are becoming a popular tool for solving many real-world problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex…

Machine Learning · Computer Science 2020-09-29 Guoliang Dong , Jingyi Wang , Jun Sun , Yang Zhang , Xinyu Wang , Ting Dai , Jin Song Dong , Xingen Wang

State of the art machine learning algorithms are highly optimized to provide the optimal prediction possible, naturally resulting in complex models. While these models often outperform simpler more interpretable models by order of…

Machine Learning · Statistics 2016-11-24 Yotam Hechtlinger

Attention mechanisms in deep learning architectures have often been used as a means of transparency and, as such, to shed light on the inner workings of the architectures. Recently, there has been a growing interest in whether or not this…

Computation and Language · Computer Science 2019-11-12 Joris Baan , Maartje ter Hoeve , Marlies van der Wees , Anne Schuth , Maarten de Rijke

Neural network interpretability is a vital component for applications across a wide variety of domains. In such cases it is often useful to analyze a network which has already been trained for its specific purpose. In this work, we develop…

Machine Learning · Computer Science 2019-11-19 Lawrence Phillips , Garrett Goh , Nathan Hodas

Black box models in machine learning have demonstrated excellent predictive performance in complex problems and high-dimensional settings. However, their lack of transparency and interpretability restrict the applicability of such models in…

Machine Learning · Computer Science 2020-06-09 Numair Sani , Jaron Lee , Razieh Nabi , Ilya Shpitser

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…

Computation and Language · Computer Science 2024-11-11 Mansi Sakarvadia

A widely used strategy to discover and understand language model mechanisms is circuit analysis. A circuit is a minimal subgraph of a model's computation graph that executes a specific task. We identify a gap in existing circuit discovery…

Machine Learning · Computer Science 2025-02-10 Tal Haklay , Hadas Orgad , David Bau , Aaron Mueller , Yonatan Belinkov

Interpretability is an important aspect of the trustworthiness of a model's predictions. Transformer's predictions are widely explained by the attention weights, i.e., a probability distribution generated at its self-attention unit (head).…

Computation and Language · Computer Science 2021-06-03 Rishabh Bhardwaj , Navonil Majumder , Soujanya Poria , Eduard Hovy

Large language models are increasingly used to process documents and facilitate question-answering on them. In our paper, we extract mechanistic circuits for this real-world language modeling task: context-augmented language modeling for…

Computation and Language · Computer Science 2025-02-13 Samyadeep Basu , Vlad Morariu , Zichao Wang , Ryan Rossi , Cherry Zhao , Soheil Feizi , Varun Manjunatha

When trained on language data, do transformers learn some arbitrary computation that utilizes the full capacity of the architecture or do they learn a simpler, tree-like computation, hypothesized to underlie compositional meaning systems…

Computation and Language · Computer Science 2022-11-07 Shikhar Murty , Pratyusha Sharma , Jacob Andreas , Christopher D. Manning

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user…

Machine Learning · Statistics 2016-06-20 Marco Tulio Ribeiro , Sameer Singh , Carlos Guestrin

AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control. Agents may skip required tool calls, invoke tools unnecessarily, or…

Artificial Intelligence · Computer Science 2026-05-22 Hariom Tatsat , Ariye Shater

Recent studies have shown that Large Language Models (LLMs) can achieve strong reasoning performance by incorporating functional symbolic representations that abstractly describe graph traversal algorithms and step-by-step reasoning in…

Artificial Intelligence · Computer Science 2026-05-28 Phuong Minh Nguyen , Tien Huu Dang , Naoya Inoue

Prompt Engineering has garnered significant attention for enhancing the performance of large language models across a multitude of tasks. Techniques such as the Chain-of-Thought not only bolster task performance but also delineate a clear…

Computation and Language · Computer Science 2024-10-21 Wei Jie Yeo , Ranjan Satapathy , Rick Siow Mong Goh , Erik Cambria