English
Related papers

Related papers: Refusal in LLMs is an Affine Function

200 papers

The standard approach to modern self-supervised learning is to generate random views through data augmentations and minimise a loss computed from the representations of these views. This inherently encourages invariance to the…

Computer Vision and Pattern Recognition · Computer Science 2024-02-15 David Torpey , Richard Klein

As Large Langue Models have been shown to memorize real-world facts, the need to update this knowledge in a controlled and efficient manner arises. Designed with these constraints in mind, Knowledge Editing (KE) approaches propose to alter…

Artificial Intelligence · Computer Science 2025-07-30 Marco Scialanga , Thibault Laugel , Vincent Grari , Marcin Detyniecki

Effective automation hinges on deciding when to act and when to escalate. We model this as a decision under uncertainty: an LLM forms a prediction, estimates its probability of being correct, and compares the expected costs of acting and…

Machine Learning · Computer Science 2026-04-13 Matthew DosSantos DiSorbo , Harang Ju

Stance classification, the task of predicting the viewpoint of an author on a subject of interest, has long been a focal point of research in domains ranging from social science to machine learning. Current stance detection methods rely…

Computation and Language · Computer Science 2024-03-07 Iain J. Cruickshank , Lynnette Hui Xian Ng

Machine learning models are increasingly used to automate decisions that affect humans - deciding who should receive a loan, a job interview, or a social service. In such applications, a person should have the ability to change the decision…

Machine Learning · Statistics 2019-11-12 Berk Ustun , Alexander Spangher , Yang Liu

The ability to steer AI behavior is crucial to preventing its long term dangerous and catastrophic potential. Representation Engineering (RepE) has emerged as a novel, powerful method to steer internal model behaviors, such as "honesty", at…

Machine Learning · Computer Science 2024-10-10 Akshat Kannan

We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior, such as its alignment, correctness, or adherence to…

Machine Learning · Computer Science 2026-02-03 Neha Kalibhat , Zi Wang , Prasoon Bajpai , Drew Proud , Wenjun Zeng , Been Kim , Mani Malek

Aspect-based sentiment analysis (ABSA) identifies sentiment information related to specific aspects and provides deeper market insights to businesses and organizations. With the emergence of large language models (LMs), recent studies have…

Computation and Language · Computer Science 2024-05-30 Guangmin Zheng , Jin Wang , Liang-Chih Yu , Xuejie Zhang

Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…

Computation and Language · Computer Science 2025-12-25 Shariqah Hossain , Lalana Kagal

Inference-time LLM alignment methods, particularly activation steering, offer an alternative to fine-tuning by directly modifying activations during generation. Existing methods, however, often rely on non-anticipative interventions that…

Machine Learning · Computer Science 2026-04-22 Julian Skifstad , Xinyue Annie Yang , Glen Chou

Adapting Large Language Models (LLMs) to downstream tasks using Reinforcement Learning (RL) has proven to be an effective approach. However, LLMs do not inherently define the structure of an agent for RL training, particularly in terms of…

Computation and Language · Computer Science 2025-03-28 Chengxing Jia , Ziniu Li , Pengyuan Wang , Yi-Chen Li , Zhenyu Hou , Yuxiao Dong , Yang Yu

Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models. This bias undermines fairness and reliability in…

Computation and Language · Computer Science 2025-09-05 Dani Roytburg , Matthew Bozoukov , Matthew Nguyen , Jou Barzdukas , Simon Fu , Narmeen Oozeer

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Machine Learning · Computer Science 2026-03-09 Kartik Sharma , Rakshit S. Trivedi

Standard LLM evaluations only test capabilities or dispositions that evaluators designed them for, missing unexpected differences such as behavioral shifts between model revisions or emergent misaligned tendencies. Model diffing addresses…

Machine Learning · Computer Science 2026-02-12 Elias Kempf , Simon Schrodi , Bartosz Cywiński , Thomas Brox , Neel Nanda , Arthur Conmy

Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations that limit domain…

Machine Learning · Computer Science 2026-05-20 Junjie Zhang , Guozheng Ma , Shunyu Liu , Zetian Hu , Yongcheng Jing , Ting-En Lin , Yongbin Li , Dacheng Tao

Recent advances in large language models (LLMs) have led to the development of thinking language models that generate extensive internal reasoning chains before producing responses. While these models achieve improved performance,…

Machine Learning · Computer Science 2025-10-23 Constantin Venhoff , Iván Arcuschin , Philip Torr , Arthur Conmy , Neel Nanda

We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback.…

In this work, we measure the impact of affixal negation on modern English large language models (LLMs). In affixal negation, the negated meaning is expressed through a negative morpheme, which is potentially challenging for LLMs as their…

Computation and Language · Computer Science 2024-04-05 Thinh Hung Truong , Yulia Otmakhova , Karin Verspoor , Trevor Cohn , Timothy Baldwin

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Computation and Language · Computer Science 2024-12-03 Oliver Kramer , Jill Baumann

LLM-based Automatic Prompt Optimization, which typically utilizes LLMs as Prompt Optimizers to self-reflect and refine prompts, has shown promising performance in recent studies. Despite the success, the underlying mechanism of this…

Computation and Language · Computer Science 2024-02-06 Ruotian Ma , Xiaolei Wang , Xin Zhou , Jian Li , Nan Du , Tao Gui , Qi Zhang , Xuanjing Huang