English
Related papers

Related papers: NEAT: Concept driven Neuron Attribution in LLMs

200 papers

Large Language Models (LLMs) have emerged as dominant foundational models in modern NLP. However, the understanding of their prediction processes and internal mechanisms, such as feed-forward networks (FFN) and multi-head self-attention…

Computation and Language · Computer Science 2024-04-16 Xintong Wang , Xiaoyu Li , Xingshan Li , Chris Biemann

Large language models (LLMs) exhibit strong multilingual abilities, yet the neural mechanisms behind language-specific processing remain unclear. We analyze language-specific neurons in Llama-3.1-8B, Mistral-Nemo-12B, and Aya-Expanse-8B &…

Computation and Language · Computer Science 2025-11-04 Daniil Gurgurov , Katharina Trinley , Yusser Al Ghussin , Tanja Baeumel , Josef van Genabith , Simon Ostermann

Large language models (LLMs) frequently generate hallucinations -- plausible but factually incorrect outputs -- undermining their reliability. While prior work has examined hallucinations from macroscopic perspectives such as training data…

Artificial Intelligence · Computer Science 2025-12-03 Cheng Gao , Huimin Chen , Chaojun Xiao , Zhiyi Chen , Zhiyuan Liu , Maosong Sun

The use of large pretrained neural networks to create contextualized word embeddings has drastically improved performance on several natural language processing (NLP) tasks. These computationally expensive models have begun to be applied to…

Computers and Society · Computer Science 2019-12-03 Benjamin Clavié , Kobi Gal

The predictive power of neural networks often costs model interpretability. Several techniques have been developed for explaining model outputs in terms of input features; however, it is difficult to translate such interpretations into…

Machine Learning · Computer Science 2017-08-17 Benjamin J. Lengerich , Sandeep Konam , Eric P. Xing , Stephanie Rosenthal , Manuela Veloso

Based on official estimates, 50 million people worldwide are affected by dementia, and this number increases by 10 million new patients every year. Without a cure, clinical prognostication and early intervention represent the most effective…

Computation and Language · Computer Science 2024-09-06 Francisco de Arriba-Pérez , Silvia García-Méndez

We propose a test for abstract causal reasoning in AI, based on scholarship in the philosophy of causation, in particular on the neuron diagrams popularized by D. Lewis. We illustrate the test on advanced Large Language Models (ChatGPT,…

Artificial Intelligence · Computer Science 2025-06-18 Louis Vervoort , Vitaly Nikolaev

Rapid advancements in Large Language models (LLMs) has significantly enhanced their reasoning capabilities. Despite improved performance on benchmarks, LLMs exhibit notable gaps in their cognitive processes. Additionally, as reflections of…

Computation and Language · Computer Science 2024-12-06 Ammar Shaikh , Raj Abhijit Dandekar , Sreedath Panat , Rajat Dandekar

Large Language Models (LLMs) have shown impressive performance on complex tasks through Chain-of-Thought (CoT) reasoning. However, conventional CoT relies on explicitly verbalized intermediate steps, which constrains its broader…

Computation and Language · Computer Science 2025-11-04 Xinghao Chen , Anhao Zhao , Heming Xia , Xuan Lu , Hanlin Wang , Yanjun Chen , Wei Zhang , Jian Wang , Wenjie Li , Xiaoyu Shen

An exhaustive study on neural network language modeling (NNLM) is performed in this paper. Different architectures of basic neural network language models are described and examined. A number of different improvements over basic neural…

Computation and Language · Computer Science 2017-08-25 Dengliang Shi

We find arithmetic ability resides within a limited number of attention heads, with each head specializing in distinct operations. To delve into the reason, we introduce the Comparative Neuron Analysis (CNA) method, which identifies an…

Computation and Language · Computer Science 2024-09-24 Zeping Yu , Sophia Ananiadou

Although deep neural networks have shown well-performance in various tasks, the poor interpretability of the models is always criticized. In the paper, we propose a new interpretable neural network method, by embedding neurons into the…

Machine Learning · Computer Science 2022-11-16 Wei Han , Yangqiming Wang , Christian Böhm , Junming Shao

Creative thinking is a fundamental aspect of human cognition, and divergent thinking-the capacity to generate novel and varied ideas-is widely regarded as its core generative engine. Large language models (LLMs) have recently demonstrated…

Topic modeling is a fundamental task in natural language processing, allowing the discovery of latent thematic structures in text corpora. While Large Language Models (LLMs) have demonstrated promising capabilities in topic discovery, their…

Computation and Language · Computer Science 2025-06-03 Xiaohao Yang , He Zhao , Weijie Xu , Yuanyuan Qi , Jueqing Lu , Dinh Phung , Lan Du

It is widely acknowledged that large language models (LLMs) encode a vast reservoir of knowledge after being trained on mass data. Recent studies disclose knowledge conflicts in LLM generation, wherein outdated or incorrect parametric…

Computation and Language · Computer Science 2024-11-15 Dan Shi , Renren Jin , Tianhao Shen , Weilong Dong , Xinwei Wu , Deyi Xiong

Providing knowledge documents for large language models (LLMs) has emerged as a promising solution to update the static knowledge inherent in their parameters. However, knowledge in the document may conflict with the memory of LLMs due to…

Computation and Language · Computer Science 2024-04-05 Yantao Liu , Zijun Yao , Xin Lv , Yuchen Fan , Shulin Cao , Jifan Yu , Lei Hou , Juanzi Li

We propose Next Concept Prediction (NCP), a generative pretraining paradigm built on top of Next Token Prediction (NTP). NCP predicts discrete concepts that span multiple tokens, thereby forming a more challenging pretraining objective. Our…

Computation and Language · Computer Science 2026-02-10 Yuliang Liu , Yunchong Song , Yixuan Wang , Kewen Ge , Alex Lamb , Qipeng Guo , Kai Chen , Bowen Zhou , Zhouhan Lin

Some neurons in deep networks specialize in recognizing highly specific perceptual, structural, or semantic features of inputs. In computer vision, techniques exist for identifying neurons that respond to individual concept categories like…

Computer Vision and Pattern Recognition · Computer Science 2022-04-19 Evan Hernandez , Sarah Schwettmann , David Bau , Teona Bagashvili , Antonio Torralba , Jacob Andreas

Probing and enhancing large language models' reasoning capacity remains a crucial open question. Here we re-purpose the reverse dictionary task as a case study to probe LLMs' capacity for conceptual inference. We use in-context learning to…

Computation and Language · Computer Science 2024-02-27 Ningyu Xu , Qi Zhang , Menghan Zhang , Peng Qian , Xuanjing Huang

Concept-based explanation methods, such as Concept Activation Vectors, are potent means to quantify how abstract or high-level characteristics of input data influence the predictions of complex deep neural networks. However, applying them…

Machine Learning · Computer Science 2023-10-18 Thomas Decker , Michael Lebacher , Volker Tresp