English
Related papers

Related papers: Towards Effective Theory of LLMs: A Representation…

200 papers

As large language models (LLMs) move from static reasoning tasks toward dynamic environments, their success depends on the ability to navigate and respond to an environment that changes as they interact at inference time. An underexplored…

Computation and Language · Computer Science 2026-02-19 Annie Wong , Aske Plaat , Thomas Bäck , Niki van Stein , Anna V. Kononova

Deep learning methods capable of handling relational data have proliferated over the last years. In contrast to traditional relational learning methods that leverage first-order logic for representing such data, these deep learning methods…

Machine Learning · Computer Science 2020-03-25 Sebastijan Dumancic , Tias Guns , Wannes Meert , Hendrik Blockeel

Large Language Models (LLMs) have shown exceptional performance in text processing. Notably, LLMs can synthesize information from large datasets and explain their decisions similarly to human reasoning through a chain of thought (CoT). An…

Computation and Language · Computer Science 2024-06-10 Michał Romaszewski , Przemysław Sekuła , Przemysław Głomb , Michał Cholewa , Katarzyna Kołodziej

We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting the forget-representations, that is, latent representations of forget-samples, toward a target…

Machine Learning · Computer Science 2026-05-18 Tien Dang , The-Hai Nguyen , Dinh Mai Phuong , Nguyen Minh Phuong , Anh Bui , Hoang Thanh-Tung , Le-Minh Nguyen , Naoya Inoue

Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…

Computation and Language · Computer Science 2026-01-08 Roy Xie , David Qiu , Deepak Gopinath , Dong Lin , Yanchao Sun , Chong Wang , Saloni Potdar , Bhuwan Dhingra

Exploration is an extremely challenging problem in reinforcement learning, especially in high dimensional state and action spaces and when only sparse rewards are available. Effective representations can indicate which components of the…

Machine Learning · Computer Science 2019-05-31 Giulia Vezzani , Abhishek Gupta , Lorenzo Natale , Pieter Abbeel

Large language models (LLMs) are often portrayed as merely imitating linguistic patterns without genuine understanding. We argue that recent findings in mechanistic interpretability (MI), the emerging field probing the inner workings of…

Computation and Language · Computer Science 2026-02-26 Pierre Beckmann , Matthieu Queloz

Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…

Computation and Language · Computer Science 2024-06-05 Henry Conklin , Kenny Smith

Large Language Models (LLMs) trained via Reinforcement Learning (RL) have exhibited strong reasoning capabilities and emergent reflective behaviors, such as rethinking and error correction, as a form of in-context exploration. However, the…

Machine Learning · Computer Science 2025-12-09 Shenao Zhang , Yaqing Wang , Yinxiao Liu , Tianqi Liu , Peter Grabowski , Eugene Ie , Zhaoran Wang , Yunxuan Li

Understanding how Large Language Models (LLMs) perform complex reasoning and their failure mechanisms is a challenge in interpretability research. To provide a measurable geometric analysis perspective, we define the concept of the…

Artificial Intelligence · Computer Science 2025-09-29 Bo Li , Guanzhi Deng , Ronghao Chen , Junrong Yue , Shuo Zhang , Qinghua Zhao , Linqi Song , Lijie Wen

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

Computation and Language · Computer Science 2024-11-27 Tim Hartill

Sentence representations are a critical component in NLP applications such as retrieval, question answering, and text classification. They capture the meaning of a sentence, enabling machines to understand and reason over human language. In…

Computation and Language · Computer Science 2024-02-05 Abhinav Ramesh Kashyap , Thanh-Tung Nguyen , Viktor Schlegel , Stefan Winkler , See-Kiong Ng , Soujanya Poria

This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…

Computation and Language · Computer Science 2025-08-27 Omar Mahmoud , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Structured representations, exemplified by Abstract Meaning Representation (AMR), have long been pivotal in computational linguistics. However, their role remains ambiguous in the Large Language Models (LLMs) era. Initial attempts to…

Computation and Language · Computer Science 2025-02-21 Jiahuan Zhang , Tianheng Wang , Hanqing Wu , Ziyi Huang , Yulong Wu , Dongbai Chen , Linfeng Song , Yue Zhang , Guozheng Rao , Kaicheng Yu

To effectively perform the task of next-word prediction, long short-term memory networks (LSTMs) must keep track of many types of information. Some information is directly related to the next word's identity, but some is more secondary…

Computation and Language · Computer Science 2021-06-01 Qingfeng Lan , Luke Kumar , Martha White , Alona Fyshe

Interpretability and explainability of AI are becoming increasingly important in light of the rapid development of large language models (LLMs). This paper investigates the interpretation of LLMs in the context of the knowledge-based…

Computation and Language · Computer Science 2024-06-05 Valeriya Goloviznina , Evgeny Kotelnikov

Recent works have argued that high-level semantic concepts are encoded "linearly" in the representation space of large language models. In this work, we study the origins of such linear representations. To that end, we introduce a simple…

Computation and Language · Computer Science 2024-03-07 Yibo Jiang , Goutham Rajendran , Pradeep Ravikumar , Bryon Aragam , Victor Veitch

Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in…

Machine Learning · Computer Science 2025-12-22 Mengdan Zhu , Raasikh Kanjiani , Jiahui Lu , Andrew Choi , Qirui Ye , Liang Zhao

This work characterizes large language models' chain-of-thought generation as a structured trajectory through representation space. We show that mathematical reasoning traverses functionally ordered, step-specific subspaces that become…

Computation and Language · Computer Science 2026-04-08 Lihao Sun , Hang Dong , Bo Qiao , Qingwei Lin , Dongmei Zhang , Saravan Rajmohan

This paper investigates models of event implications. Specifically, how well models predict entity state-changes, by targeting their understanding of physical attributes. Nominally, Large Language models (LLM) have been exposed to…

Computation and Language · Computer Science 2022-11-11 Evangelia Spiliopoulou , Artidoro Pagnoni , Yonatan Bisk , Eduard Hovy