English
Related papers

Related papers: Flash Interpretability: Decoding Specialised Featu…

200 papers

Large language models (LLMs) have been shown to be capable of impressive few-shot generalisation to new tasks. However, they still tend to perform poorly on multi-step logical reasoning problems. Here we carry out a comprehensive evaluation…

Artificial Intelligence · Computer Science 2022-05-20 Antonia Creswell , Murray Shanahan , Irina Higgins

Large language models exhibit a puzzling inconsistency: they solve complex problems yet frequently fail on seemingly simpler ones. We investigate whether LLMs internally encode problem difficulty in a way that aligns with human judgment,…

Computation and Language · Computer Science 2025-10-22 William Lugoloobi , Chris Russell

Recent findings reveal that much of the knowledge in a Transformer-based Large Language Model (LLM) is encoded in its feed-forward (FFN) layers, where each FNN layer can be interpreted as the summation of sub-updates, each corresponding to…

Computation and Language · Computer Science 2025-07-01 Ying Shen , Lifu Huang

Large Language Models (LLMs) have rapidly transformed the landscape of artificial intelligence, enabling natural language interfaces and dynamic orchestration of software components. However, their reliance on probabilistic inference limits…

Machine Learning · Computer Science 2025-07-01 Claudionor Coelho , Yanen Li , Philip Tee

Pre-trained Large Language Models (LLMs) have shown success in a diverse set of language inference and understanding tasks. The pre-training stage of LLMs looks at a large corpus of raw textual data. The BabyLM shared task compares LLM…

Computation and Language · Computer Science 2024-01-11 Khushi Bhardwaj , Raj Sanjay Shah , Sashank Varma

We propose a novel framework that leverages large language models (LLMs) to guide the rank selection in tensor network models for higher-order data analysis. By utilising the intrinsic reasoning capabilities and domain knowledge of LLMs,…

Machine Learning · Computer Science 2024-10-15 Giorgos Iacovides , Wuyang Zhou , Danilo Mandic

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Large Language Models (LLMs) struggle to perform such reasoning consistently. Here we propose an approach to pinpoint and rectify…

Computation and Language · Computer Science 2024-03-01 Mansi Sakarvadia , Aswathy Ajith , Arham Khan , Daniel Grzenda , Nathaniel Hudson , André Bauer , Kyle Chard , Ian Foster

Interpretability researchers have attempted to understand MLP neurons of language models based on both the contexts in which they activate and their output weight vectors. They have paid little attention to a complementary aspect: the…

Machine Learning · Computer Science 2025-05-26 Sebastian Gerstner , Hinrich Schütze

In this work, we observe an interesting phenomenon: it is possible to generate reversible sentence embeddings that allow an LLM to reconstruct the original text exactly, without modifying the model's weights. This is achieved by introducing…

Computation and Language · Computer Science 2026-01-09 Ignacio Sastre , Aiala Rosá

Understanding the inner workings of large language models (LLMs) is crucial for advancing their theoretical foundations and real-world applications. While the attention mechanism and multi-layer perceptrons (MLPs) have been studied…

Computation and Language · Computer Science 2024-10-24 Clement Neo , Shay B. Cohen , Fazl Barez

Deep Neural Networks use thousands of mostly incomprehensible features to identify a single class, a decision no human can follow. We propose an interpretable sparse and low dimensional final decision layer in a deep neural network with…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Thomas Norrenbrock , Marco Rudolph , Bodo Rosenhahn

Locating neurons that are responsible for final predictions is important for opening the black-box large language models and understanding the inside mechanisms. Previous studies have tried to find mechanisms that operate at the neuron…

Computation and Language · Computer Science 2025-08-25 Vivek Hruday Kavuri , Gargi Shroff , Rahul Mishra

The surprising ability of Large Language Models (LLMs) to perform well on complex reasoning with only few-shot chain-of-thought prompts is believed to emerge only in very large-scale models (100+ billion parameters). We show that such…

Computation and Language · Computer Science 2023-01-31 Yao Fu , Hao Peng , Litu Ou , Ashish Sabharwal , Tushar Khot

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

Computation and Language · Computer Science 2025-01-31 Didier Chételat , Joseph Cotnareanu , Rylee Thompson , Yingxue Zhang , Mark Coates

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

Multimodal Large Language Models (MLLMs) have demonstrated strong performance across a wide range of vision-language tasks, yet their internal processing dynamics remain underexplored. In this work, we introduce a probing framework to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Zhuoran Yu , Yong Jae Lee

The remarkable success of large language models (LLMs) stems from their ability to consolidate vast amounts of knowledge into the memory during pre-training and to retrieve it from the memory during inference, enabling advanced capabilities…

Computation and Language · Computer Science 2025-10-10 Shaohua Zhang , Yuan Lin , Hang Li

We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72-95% of their original top-1 prediction accuracy without any…

Machine Learning · Computer Science 2025-06-17 Vedang Lad , Jin Hwa Lee , Wes Gurnee , Max Tegmark

Existing Multimodal Large Language Models (MLLMs) process a large number of visual tokens, leading to significant computational costs and inefficiency. Instruction-related visual token compression demonstrates strong task relevance, which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Lei Lei , Jie Gu , Xiaokang Ma , Chu Tang , Jingmin Chen , Tong Xu

Large language models (LLMs) exhibit failures on elementary symbolic tasks such as character counting in a word, despite excelling on complex benchmarks. Although this limitation has been noted, the internal reasons remain unclear. We use…

Computation and Language · Computer Science 2026-04-02 Ayan Datta , Mounika Marreddy , Alexander Mehler , Zhixue Zhao , Radhika Mamidi
‹ Prev 1 4 5 6 7 8 10 Next ›