English
Related papers

Related papers: Weird Generalization and Inductive Backdoors: New …

200 papers

Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…

Cryptography and Security · Computer Science 2024-06-11 Yuanpu Cao , Bochuan Cao , Jinghui Chen

This thesis provides methods and analysis of models which make progress on this goal. The techniques outlined are task agnostic, and should provide benefit when used with nearly any transformer LM. We introduce two new finetuning methods…

Computation and Language · Computer Science 2024-08-30 Davis Yoshida

Large language models (LLMs) exhibit cognitive biases -- systematic tendencies of irrational decision-making, similar to those seen in humans. Prior work has found that these biases vary across models and can be amplified by instruction…

Computation and Language · Computer Science 2025-07-15 Itay Itzhak , Yonatan Belinkov , Gabriel Stanovsky

We demonstrate that LLMs may learn indicators of document usefulness and modulate their updates accordingly. We introduce random strings ("tags") as indicators of usefulness in a synthetic fine-tuning dataset. Fine-tuning on this dataset…

Machine Learning · Computer Science 2024-07-16 Dmitrii Krasheninnikov , Egor Krasheninnikov , Bruno Mlodozeniec , Tegan Maharaj , David Krueger

Given the prevalence of pre-trained contextualized representations in today's NLP, there have been many efforts to understand what information they contain, and why they seem to be universally successful. The most common approach to use…

Computation and Language · Computer Science 2022-03-17 Yichu Zhou , Vivek Srikumar

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generate incorrect outputs in the presence of specific, often…

Machine Learning · Computer Science 2025-03-25 Sharon Lin , Krishnamurthy , Dvijotham , Jamie Hayes , Chongyang Shi , Ilia Shumailov , Shuang Song

Large Language Models (LLMs) are a transformational technology, fundamentally changing how people obtain information and interact with the world. As people become increasingly reliant on them for an enormous variety of tasks, a body of…

Computers and Society · Computer Science 2025-05-08 Nouar Aldahoul , Hazem Ibrahim , Matteo Varvello , Aaron Kaufman , Talal Rahwan , Yasir Zaki

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam

Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse…

Artificial Intelligence · Computer Science 2026-02-03 Abhishek Mishra , Mugilan Arulvanan , Reshma Ashok , Polina Petrova , Deepesh Suranjandass , Donnie Winkelmann

Recent advancements in cognitive science and multi-round reasoning techniques for Large Language Models (LLMs) suggest that iterative thinking processes improve problem-solving performance in complex tasks. Inspired by this, approaches like…

Artificial Intelligence · Computer Science 2025-03-06 Chenhui Xu , Dancheng Liu , Jiajie Li , Amir Nassereldine , Zhaohui Li , Jinjun Xiong

Large language models (LLMs) have been able to perform various forms of reasoning tasks in a wide range of scenarios, but are they truly engaging in task abstraction and rule-based reasoning beyond mere memorization? To answer this…

Machine Learning · Computer Science 2025-12-09 Guanyu Chen , Peiyang Wang , Yizhou Jiang , Yuqian Liu , Chujie Zhao , Ying Fang , Tianren Zhang , Feng Chen

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Computation and Language · Computer Science 2025-06-03 Vera Neplenbroek , Arianna Bisazza , Raquel Fernández

Fine-tuned LLMs often exhibit unexpected behavior as a result of generalizing beyond the data they're shown. We present results in which an LLM fine-tuned to prefer either coastal sports teams or Southern sports teams adopt political…

Physics and Society · Physics 2026-01-23 Owen Terry

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable outputs. While such…

Cryptography and Security · Computer Science 2024-07-19 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Farhan Ahmed , Ling Cai , Nathalie Baracaldo

Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the…

Computation and Language · Computer Science 2025-11-04 Riccardo Alberghi , Elizaveta Demyanenko , Luca Biggio , Luca Saglietti

Large Language Models (LLMs) have the unique capability to understand and generate human-like text from input queries. When fine-tuned, these models show enhanced performance on domain-specific queries. OpenAI highlights the process of…

Computation and Language · Computer Science 2024-07-02 Scott Barnett , Zac Brannelly , Stefanus Kurniawan , Sheng Wong

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…

Cryptography and Security · Computer Science 2026-03-05 Bhanu Pallakonda , Mikkel Hindsbo , Sina Ehsani , Prag Mishra

Large Language Models (LLMs) fine-tuned for specific domains exhibit strong performance; however, the underlying mechanisms by which this fine-tuning reshapes their parametric space are not well understood. Prior works primarily focus on…

Computation and Language · Computer Science 2025-10-13 Eshaan Tanwar , Deepak Nathani , William Yang Wang , Tanmoy Chakraborty

Due to the high cost of training, large model (LM) practitioners commonly use pretrained models downloaded from untrusted sources, which could lead to owning compromised models. In-context learning is the ability of LMs to perform multiple…

Cryptography and Security · Computer Science 2024-09-09 Gorka Abad , Stjepan Picek , Lorenzo Cavallaro , Aitor Urbieta