English
Related papers

Related papers: Refusal in LLMs is an Affine Function

200 papers

This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Anushka Sivakumar , Andrew Zhang , Zaber Hakim , Chris Thomas

Large Vision-Language Models (LVLMs) have achieved substantial progress in cross-modal tasks. However, due to language bias, LVLMs are susceptible to object hallucination, which can be primarily divided into category, attribute, and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Tianbo Wang , Yuqing Ma , Kewei Liao , Zhange Zhang , Simin Li , Jinyang Guo , Xianglong Liu

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences.…

Computation and Language · Computer Science 2024-06-27 Wasu Top Piriyakulkij , Volodymyr Kuleshov , Kevin Ellis

Representation Engineering (RepE) is a novel paradigm for controlling the behavior of LLMs. Unlike traditional approaches that modify inputs or fine-tune the model, RepE directly manipulates the model's internal representations. As a…

Machine Learning · Computer Science 2025-10-09 Jan Wehner , Sahar Abdelnabi , Daniel Tan , David Krueger , Mario Fritz

Large language models (LLMs) have made impressive progress in natural language processing. These models rely on proper human instructions (or prompts) to generate suitable responses. However, the potential of LLMs are not fully harnessed by…

Computation and Language · Computer Science 2023-10-24 Xinyu Hu , Pengfei Tang , Simiao Zuo , Zihan Wang , Bowen Song , Qiang Lou , Jian Jiao , Denis Charles

Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified…

Biomolecules · Quantitative Biology 2025-09-15 Long-Kai Huang , Rongyi Zhu , Bing He , Jianhua Yao

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

The safety alignment of large language models (LLMs) can be circumvented through adversarially crafted inputs, yet the mechanisms by which these attacks bypass safety barriers remain poorly understood. Prior work suggests that a single…

Large Language Models (LLMs) are being increasingly explored as general-purpose tools for recommendation tasks, enabling zero-shot and instruction-following capabilities without the need for task-specific training. While the research…

Information Retrieval · Computer Science 2025-08-05 Ethan Bito , Yongli Ren , Estrid He

Large language models are becoming the go-to solution for the ever-growing number of tasks. However, with growing capacity, models are prone to rely on spurious correlations stemming from biases and stereotypes present in the training data.…

Computation and Language · Computer Science 2024-05-30 Tomasz Limisiewicz , David Mareček , Tomáš Musil

We study how Large Language Models (LLMs) process negation mechanistically. First, we establish that even though open-weight models often provide wrong answers to questions involving negation, they do possess internal components that…

Computation and Language · Computer Science 2026-05-06 Zhejian Zhou , Tianyi Zhou , Robin Jia , Jonathan May

While Vision-Language Models (VLMs) offer rich world knowledge for end-to-end autonomous driving, current approaches heavily rely on labor-intensive language annotations (e.g., VQA) to bridge perception and control. This paradigm suffers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Chengen Xie , Chonghao Sima , Tianyu Li , Bin Sun , Junjie Wu , Zhihui Hao , Hongyang Li

We present the Mixture-of-Tunable-Experts (MoTE), a method that extends the Mixture-of-Experts architecture of Large Language Models (LLMs). Without additional training, MoTE enables meaningful and focused behavior changes in LLMs…

Artificial Intelligence · Computer Science 2025-02-21 Robert Dahlke , Henrik Klagges , Dan Zecha , Benjamin Merkel , Sven Rohr , Fabian Klemm

The alignments of reasoning abilities between smaller and larger Language Models are largely conducted via Supervised Fine-Tuning (SFT) using demonstrations generated from robust Large Language Models (LLMs). Although these approaches…

Computation and Language · Computer Science 2025-01-28 Leonardo Ranaldi , Andrè Freitas

Model editing aims to modify the outputs of large language models after they are trained. Previous approaches have often involved direct alterations to model weights, which can result in model degradation. Recent techniques avoid making…

Computation and Language · Computer Science 2025-10-10 Hammad Rizwan , Domenic Rosati , Ga Wu , Hassan Sajjad

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Computation and Language · Computer Science 2025-05-20 Jian-Qiao Zhu , Haijiang Yan , Thomas L. Griffiths

While large language models (LLMs) have increasingly been applied to hate speech detoxification, the prompts often trigger safety alerts, causing LLMs to refuse the task. In this study, we systematically investigate false refusal behavior…

Computation and Language · Computer Science 2026-01-14 Kyuri Im , Shuzhou Yuan , Michael Färber

As large language models (LLMs) advance, it becomes more challenging to reliably evaluate their output due to the high costs of human evaluation. To make progress towards better LLM autoraters, we introduce FLAMe, a family of Foundational…

Computation and Language · Computer Science 2024-07-16 Tu Vu , Kalpesh Krishna , Salaheddin Alzubi , Chris Tar , Manaal Faruqui , Yun-Hsuan Sung

In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that LLMs can detect and…

Computation and Language · Computer Science 2023-11-15 Kumar Shridhar , Koustuv Sinha , Andrew Cohen , Tianlu Wang , Ping Yu , Ram Pasunuru , Mrinmaya Sachan , Jason Weston , Asli Celikyilmaz

Large Language Models (LLMs) often struggle with deductive judgment in syllogistic reasoning, systematically conflating semantic plausibility with formal validity a phenomenon known as content effect. This bias persists even when models…

Computation and Language · Computer Science 2026-02-03 Gabriele Maraia , Marco Valentino , Fabio Massimo Zanzotto , Leonardo Ranaldi
‹ Prev 1 8 9 10 Next ›