English
Related papers

Related papers: Manifold-Guided Attention Steering

200 papers

Multimodal Retrieval-Augmented Generation (MRAG) addresses key limitations of Multimodal Large Language Models (MLLMs), such as hallucination and outdated knowledge. However, current MRAG systems struggle to distinguish whether retrieved…

Computation and Language · Computer Science 2026-05-01 Xihang Wang , Zihan Wang , Chengkai Huang , Quan Z. Sheng , Lina Yao

Large Language Models have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scaling (TTS) improves reasoning quality, it often leads to…

Computation and Language · Computer Science 2026-05-26 Hang Yan , Fangzhi Xu , Rongman Xu , Yifei Li , Jian Zhang , Haoran Luo , Xiaobao Wu , Luu Anh Tuan , Haiteng Zhao , Qika Lin , Jun Liu

We introduce Mechanistic Error Reduction with Abstention (MERA), a principled framework for steering language models (LMs) to mitigate errors through selective, adaptive interventions. Unlike existing methods that rely on fixed, manually…

Machine Learning · Computer Science 2025-10-16 Anna Hedström , Salim I. Amoukou , Tom Bewley , Saumitra Mishra , Manuela Veloso

Retrieval-Augmented Generation (RAG) lifts the factuality of Large Language Models (LLMs) by injecting external knowledge, yet it falls short on problems that demand multi-step inference; conversely, purely reasoning-oriented approaches…

Activation steering methods in large language models (LLMs) have emerged as an effective way to perform targeted updates to enhance generated language without requiring large amounts of adaptation data. We ask whether the features…

Computation and Language · Computer Science 2025-11-05 Masha Fedzechkina , Eleonora Gualdoni , Sinead Williamson , Katherine Metcalf , Skyler Seto , Barry-John Theobald

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

Multimodal large language models (MLLMs) often fail in fine-grained visual question answering, producing hallucinations about object identities, positions, and relations because textual queries are not explicitly anchored to visual…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Suyang Xi , Chenxi Yang , Hong Ding , Yiqing Ni , Catherine C. Liu , Yunhao Liu , Chengqi Zhang

Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…

Computation and Language · Computer Science 2024-02-20 Zizhong Li , Haopeng Zhang , Jiawei Zhang

Steering vectors offer a training-free mechanism for controlling reasoning behaviors in large language models, but constructing effective vectors requires identifying genuine behavioral signals in the model's hidden states. For behaviors…

Computation and Language · Computer Science 2026-04-03 Haomin Zhuang , Hojun Yoo , Xiaonan Luo , Kehan Guo , Xiangliang Zhang

Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and reliance on null-condition training limit its use in few-step regimes. Attention-space guidance has emerged as a complementary…

Machine Learning · Computer Science 2026-05-19 Kwanyoung Kim

Large language models (LLMs) are able to generate grammatically well-formed text, but how do they encode their syntactic knowledge internally? While prior work has focused largely on binary grammatical contrasts, in this work, we study the…

Computation and Language · Computer Science 2025-09-16 Alina Klerings , Jannik Brinkmann , Daniel Ruffinelli , Simone Ponzetto

Self-evolving language-model agents must decide what to learn next and how to preserve what they have learned across iterations. Existing systems typically carry this cross-iteration knowledge as natural-language feedback, flat episodic…

Artificial Intelligence · Computer Science 2026-05-12 Ruiyi Yang , Zechen Li , Hao Xue , Imran Razzak , Flora D. Salim

The increase in computing power and the necessity of AI-assisted decision-making boost the growing application of large language models (LLMs). Along with this, the potential retention of sensitive data of LLMs has spurred increasing…

Computation and Language · Computer Science 2026-04-20 Chenchen Tan , Youyang Qu , Xinghao Li , Hui Zhang , Shujie Cui , Cunjian Chen , Longxiang Gao

Large language models (LLMs) have demonstrated significant improvements in contextual understanding. However, their ability to attend to truly critical information during long-context reasoning and generation still falls behind the pace.…

Computation and Language · Computer Science 2025-10-27 Yiju Guo , Wenkai Yang , Zexu Sun , Ning Ding , Zhiyuan Liu , Yankai Lin

A binary decision task, like yes-no questions or answer verification, reflects a significant real-world scenario such as where users look for confirmation about the correctness of their decisions on specific issues. In this work, we observe…

Computation and Language · Computer Science 2025-04-30 Sangwon Yu , Jongyoon Song , Bongkyu Hwang , Hoyoung Kang , Sooah Cho , Junhwa Choi , Seongho Joe , Taehee Lee , Youngjune L. Gwon , Sungroh Yoon

The fusion of Large Language Models with vision models is pioneering new possibilities in user-interactive vision-language tasks. A notable application is reasoning segmentation, where models generate pixel-level segmentation masks by…

Computer Vision and Pattern Recognition · Computer Science 2025-03-19 Donggon Jang , Yucheol Cho , Suin Lee , Taehyeon Kim , Dae-Shik Kim

Steering vectors have emerged as a lightweight and effective approach for aligning large language models (LLMs) at inference time, enabling modulation over model behaviors by shifting LLM representations towards a target behavior. However,…

Machine Learning · Computer Science 2026-04-07 Soham Gadgil , Chris Lin , Su-In Lee

Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which gradient-based learning creates the required internal…

Machine Learning · Statistics 2026-05-19 Naman Agarwal , Siddhartha R. Dalal , Vishal Misra

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…

Computation and Language · Computer Science 2026-03-30 Hongxiang Zhang , Yuan Tian , Tianyi Zhang

Large vision-language models (LVLMs) exhibit impressive ability to jointly reason over visual and textual inputs. However, they often produce outputs that are linguistically fluent but factually inconsistent with the visual evidence, i.e.,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Zihu Wang , Boxun Xu , Yuxuan Xia , Peng Li