English
Related papers

Related papers: Identifying Linear Relational Concepts in Large La…

200 papers

Large Language Models (LLMs) often exhibit a gap between their internal knowledge and their explicit linguistic outputs. In this report, we empirically investigate whether Looped Transformers (LTs)--architectures that increase computational…

Computation and Language · Computer Science 2026-01-16 Guanxu Chen , Dongrui Liu , Jing Shao

Large language models (LLMs) exhibit strong semantic understanding, yet struggle when user instructions involve ambiguous or conceptually misaligned terms. We propose the Language Graph Model (LGM) to enhance conceptual clarity by…

Computation and Language · Computer Science 2025-11-06 Wenchang Lei , Ping Zou , Yue Wang , Feng Sun , Lei Zhao

Studies of LLMs' political opinions mainly rely on evaluations of their open-ended responses. Recent work indicates that there is a misalignment between LLMs' responses and their internal intentions. This motivates us to probe LLMs'…

Computation and Language · Computer Science 2025-06-06 Jingyu Hu , Mengyue Yang , Mengnan Du , Weiru Liu

Pretrained language models (PLMs) have made significant strides in various natural language processing tasks. However, the lack of interpretability due to their ``black-box'' nature poses challenges for responsible implementation. Although…

Computation and Language · Computer Science 2023-11-10 Zhen Tan , Lu Cheng , Song Wang , Yuan Bo , Jundong Li , Huan Liu

Large Language Models (LLMs) have recently emerged as promising tools for recommendation thanks to their advanced textual understanding ability and context-awareness. Despite the current practice of training and evaluating LLM-based…

Information Retrieval · Computer Science 2025-06-12 Sein Kim , Hongseok Kang , Kibum Kim , Jiwan Kim , Donghyun Kim , Minchul Yang , Kwangjin Oh , Julian McAuley , Chanyoung Park

Large language models (LLMs) are increasingly deployed on complex reasoning tasks, yet little is known about their ability to internally evaluate problem difficulty, which is an essential capability for adaptive reasoning and efficient…

Computation and Language · Computer Science 2025-10-14 Sunbowen Lee , Qingyu Yin , Chak Tou Leong , Jialiang Zhang , Yicheng Gong , Shiwen Ni , Min Yang , Xiaoyu Shen

Large language models (LLMs) have demonstrated broad utility across molecular domains, spanning drug discovery and materials design. Analyzing LLMs' latent representations is crucial for elucidating their underlying mechanisms, improving…

Machine Learning · Computer Science 2026-02-03 Zhuoran Li , Xu Sun , Wanyu Lin , Jiannong Cao

This paper aims to bridge the affective gap between image content and the emotional response of the viewer it elicits by using High-Level Concepts (HLCs). In contrast to previous work that relied solely on low-level features or used…

Computer Vision and Pattern Recognition · Computer Science 2017-05-09 Afsheen Rafaqat Ali , Usman Shahid , Mohsen Ali , Jeffrey Ho

Analogical reasoning relies on conceptual abstractions, but it is unclear whether Large Language Models (LLMs) harbor such internal representations. We explore distilled representations from LLM activations and find that function vectors…

Computation and Language · Computer Science 2025-03-06 Gustaw Opiełka , Hannes Rosenbusch , Claire E. Stevenson

Neural network models of language have long been used as a tool for developing hypotheses about conceptual representation in the mind and brain. For many years, such use involved extracting vector-space representations of words and using…

Artificial Intelligence · Computer Science 2023-11-13 Siddharth Suresh , Kushin Mukherjee , Xizheng Yu , Wei-Chun Huang , Lisa Padua , Timothy T Rogers

We study how large language models recall relational knowledge during text generation, with a focus on identifying latent representations suitable for relation classification via linear probes. Prior work shows how attention heads and MLPs…

Computation and Language · Computer Science 2026-04-24 Nicholas Popovič , Michael Färber

We introduce the Concept Bottleneck Large Language Model (CB-LLM), a pioneering approach to creating inherently interpretable Large Language Models (LLMs). Unlike traditional black-box LLMs that rely on post-hoc interpretation methods with…

Computation and Language · Computer Science 2024-07-08 Chung-En Sun , Tuomas Oikarinen , Tsui-Wei Weng

Language is typically modelled with discrete sequences. However, the most successful approaches to language modelling, namely neural networks, are continuous and smooth function approximators. In this work, we show that Transformer-based…

Computation and Language · Computer Science 2025-04-08 Samuele Marro , Davide Evangelista , X. Angelo Huang , Emanuele La Malfa , Michele Lombardi , Michael Wooldridge

Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…

Computation and Language · Computer Science 2025-10-14 Hyeonbin Hwang , Byeongguk Jeon , Seungone Kim , Jiyeon Kim , Hoyeon Chang , Sohee Yang , Seungpil Won , Dohaeng Lee , Youbin Ahn , Minjoon Seo

Understanding human intents from multimodal signals is critical for analyzing human behaviors and enhancing human-machine interactions in real-world scenarios. However, existing methods exhibit limitations in their modality-level reliance,…

Multimedia · Computer Science 2025-09-03 Qianrui Zhou , Hua Xu , Yifan Wang , Xinzhi Dong , Hanlei Zhang

To build intelligent machine learning systems, there are two broad approaches. One approach is to build inherently interpretable models, as endeavored by the growing field of causal representation learning. The other approach is to build…

Machine Learning · Computer Science 2024-12-10 Goutham Rajendran , Simon Buchholz , Bryon Aragam , Bernhard Schölkopf , Pradeep Ravikumar

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Machine Learning · Computer Science 2026-02-03 Parmida Davarmanesh , Ashia Wilson , Adityanarayanan Radhakrishnan

Deep learning has advanced NLP, but interpretability remains limited, especially in healthcare and finance. Concept bottleneck models tie predictions to human concepts in vision, but NLP versions either use binary activations that harm text…

Computation and Language · Computer Science 2026-03-31 Yibo Yang

Large Language Models (LLMs) have been successfully used in many natural-language tasks and applications including text generation and AI chatbots. They also are a promising new technology for concept-oriented deep learning (CODL). However,…

Machine Learning · Computer Science 2023-09-21 Daniel T. Chang

Reward models (RMs) are a crucial component in the alignment of large language models' (LLMs) outputs with human values. RMs approximate human preferences over possible LLM responses to the same prompt by predicting and comparing reward…

Machine Learning · Computer Science 2025-02-27 Junqi Jiang , Tom Bewley , Saumitra Mishra , Freddy Lecue , Manuela Veloso