English
Related papers

Related papers: Latent Concept-based Explanation of NLP Models

200 papers

What happens when a language model thinks without words? Standard reasoning LLMs verbalize intermediate steps as chain-of-thought; latent reasoning transformers (LRTs) instead perform deliberation entirely in continuous hidden space. We…

Computation and Language · Computer Science 2026-02-10 Jasmine Cui , Charles Ye

Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens. Consequently, they lack an inherent incentive to compress history into compact latent states with…

Compressing long chains of thought (CoT) into compact latent tokens is crucial for efficient reasoning with large language models (LLMs). Recent studies employ autoencoders to achieve this by reconstructing textual CoT from latent tokens,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Xiaoshu Chen , Sihang Zhou , Ke Liang , Taichun Zhou , Xinwang Liu

Layer-wise Relevance Propagation (LRP) and saliency maps have been recently used to explain the predictions of Deep Learning models, specifically in the domain of text classification. Given different attribution-based explanations to…

Information Retrieval · Computer Science 2018-12-04 Wenting Xiong , Iftitahu Ni'mah , Juan M. G. Huesca , Werner van Ipenburg , Jan Veldsink , Mykola Pechenizkiy

Deep neural networks that yield human interpretable decisions by architectural design have lately become an increasingly popular alternative to post hoc interpretation of traditional black-box models. Among these networks, the arguably most…

Computer Vision and Pattern Recognition · Computer Science 2021-06-24 Adrian Hoffmann , Claudio Fanconi , Rahul Rade , Jonas Kohler

Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hinders real-world deployment in latency-sensitive recommender…

Information Retrieval · Computer Science 2026-05-12 Yiwen Chen , Fuwei Zhang , Zehao Chen , Deqing Wang , Hehan Li , Peizhi Xu , Hanmeng Liu , Shuanglong Li , Xin Pei , Fuzhen Zhuang , Zhao Zhang

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question…

Computation and Language · Computer Science 2021-09-06 Paul Michel

This paper presents NoisyCoconut, a novel inference-time method that enhances large language model (LLM) reliability by manipulating internal representations. Unlike fine-tuning methods that require extensive retraining, NoisyCoconut…

Machine Learning · Computer Science 2026-05-12 Michael Jerge , David Evans

Semantic representation and inference is essential for Natural Language Processing (NLP). The state of the art for semantic representation and inference is deep learning, and particularly Recurrent Neural Networks (RNNs), Convolutional…

Computation and Language · Computer Science 2021-06-16 Dongsheng Wang

*Concept-based explanations* offer a promising approach for explaining the predictions of deep neural networks in terms of high-level, human-understandable concepts. However, existing methods either do not establish a causal connection…

Machine Learning · Computer Science 2026-05-08 Ronaldo Canizales , Divya Gopinath , Corina Păsăreanu , Ravi Mangal

We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent…

Computation and Language · Computer Science 2018-12-12 Artidoro Pagnoni , Kevin Liu , Shangyan Li

Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…

Computation and Language · Computer Science 2020-10-13 Mengjie Zhao , Philipp Dufter , Yadollah Yaghoobzadeh , Hinrich Schütze

Part-based reasoning is a classical strategy to make a computer vision model directly focus on the object parts that are relevant to the downstream task. In the context of deep learning, this also serves to improve by-design…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Ananthu Aniraj , Cassio F. Dantas , Dino Ienco , Massimiliano Mancini , Diego Marcos

We study how to extend chain-of-thought (CoT) beyond language to better handle multimodal reasoning. While CoT helps LLMs and VLMs articulate intermediate steps, its text-only form often fails on vision-intensive problems where key…

Artificial Intelligence · Computer Science 2026-02-03 Yifei Shao , Kun Zhou , Ziming Xu , Mohammad Atif Quamar , Shibo Hao , Zhen Wang , Zhiting Hu , Biwei Huang

Complex nonlinear models such as deep neural network (DNNs) have become an important tool for image classification, speech recognition, natural language processing, and many other fields of application. These models however lack…

Neural retrieval models have superseded classic bag-of-words methods such as BM25 as the retrieval framework of choice. However, neural systems lack the interpretability of bag-of-words models; it is not trivial to connect a query change to…

We propose a novel class of language models, Latent Thought Models (LTMs), which incorporate explicit latent thought vectors that follow an explicit prior model in latent space. These latent thought vectors guide the autoregressive…

Computation and Language · Computer Science 2025-06-10 Deqian Kong , Minglu Zhao , Dehong Xu , Bo Pang , Shu Wang , Edouardo Honig , Zhangzhang Si , Chuan Li , Jianwen Xie , Sirui Xie , Ying Nian Wu

We are born with the ability to learn concepts by comparing diverse observations. This helps us to understand the new world in a compositional manner and facilitates extrapolation, as objects naturally consist of multiple concepts. In this…

Machine Learning · Computer Science 2025-10-02 Yujia Zheng , Shaoan Xie , Kun Zhang

Language models (LMs) often struggle to pay enough attention to the input context, and generate texts that are unfaithful or contain hallucinations. To mitigate this issue, we present context-aware decoding (CAD), which follows a…

Computation and Language · Computer Science 2023-05-25 Weijia Shi , Xiaochuang Han , Mike Lewis , Yulia Tsvetkov , Luke Zettlemoyer , Scott Wen-tau Yih

In the present paper we show that distributional information is particularly important when considering concept availability under implicit language learning conditions. Based on results from different behavioural experiments we argue that…

Computation and Language · Computer Science 2016-06-30 Dimitrios Alikaniotis , John N. Williams