English
Related papers

Related papers: LLM Unlearning with LLM Beliefs

200 papers

The pretrained large language models (LLMs) are finetuned with labeled data for better instruction following ability and alignment with human values. In this paper, we study the learning dynamics of LLM finetuning on reasoning tasks and…

Computation and Language · Computer Science 2025-09-30 Zhiwen Ruan , Yun Chen , Yutao Hou , Peng Li , Yang Liu , Guanhua Chen

The recent success of machine learning models, especially large-scale classifiers and language models, relies heavily on training with massive data. These data are often collected from online sources. This raises serious concerns about the…

Artificial Intelligence · Computer Science 2025-11-12 Ruihan Zhang , Jun Sun , Ee-Peng Lim , Peixin Zhang

Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis under escalating pressure. We propose \textbf{\textsc{Med-Stress}}, a targeted stress test…

Artificial Intelligence · Computer Science 2026-05-26 Boyu Xiao , Xiuqi Tian , Xuwen Song , Haochun Wang , Guanchun Song , Sendong Zhao , Bing Qin

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

Machine Learning · Computer Science 2026-05-21 Yujie Lin , Chengyi Yang , Zhishang Xiang , Yiping Song , Jinsong Su

Auto-regressive large language models (LLMs) show impressive capacities to solve many complex reasoning tasks while struggling with some simple logical reasoning tasks such as inverse search: when trained on '$A \to B$' (e.g., 'Tom is the…

Machine Learning · Computer Science 2024-10-29 Hanlin Zhu , Baihe Huang , Shaolun Zhang , Michael Jordan , Jiantao Jiao , Yuandong Tian , Stuart Russell

While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowledge internally,…

Machine Learning · Computer Science 2025-08-22 Chengcan Wu , Zeming Wei , Huanran Chen , Yinpeng Dong , Meng Sun

Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these two modes offer complementary…

Machine Learning · Computer Science 2026-04-03 Arslan Chaudhry , Sridhar Thiagarajan , Andrew Lampinen

Training large language models (LLMs) is computationally expensive, partly because the loss exhibits slow power-law convergence whose origin remains debatable. Through systematic analysis of toy models and empirical evaluation of LLMs, we…

Machine Learning · Computer Science 2026-02-04 Yizhou Liu , Ziming Liu , Cengiz Pehlevan , Jeff Gore

There have been a couple of studies showing that attempting to erase multilingual knowledge using only English data is insufficient for multilingual LLMs. However, their analyses remain highly performance-oriented. In this paper, we switch…

Computation and Language · Computer Science 2025-10-29 Kyomin Hwang , Hyeonjin Kim , Seungyeon Kim , Sunghyun Wee , Nojun Kwak

Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. Existing analyses focus on average-case scenarios, often neglecting the highly skewed…

Artificial Intelligence · Computer Science 2025-02-04 Hao Li , Di Huang , Ziyu Wang , Amir M. Rahmani

During pretraining, LLMs inadvertently memorize sensitive or copyrighted data, posing significant compliance challenges under legal frameworks like the GDPR and the EU AI Act. Fulfilling these mandates demands techniques that can remove…

Machine Learning · Computer Science 2026-03-23 Efstratios Zaradoukas , Bardh Prenkaj , Gjergji Kasneci

In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require extensive exploration and face challenges in generalizing…

Machine Learning · Computer Science 2024-10-11 Xue Yan , Yan Song , Xidong Feng , Mengyue Yang , Haifeng Zhang , Haitham Bou Ammar , Jun Wang

Large Language Models (LLMs) are powerful linguistic engines but remain susceptible to hallucinations: plausible-sounding outputs that are factually incorrect or unsupported. In this work, we present a mathematically grounded framework to…

Computation and Language · Computer Science 2025-11-20 Moses Kiprono

Large language model (LLM) unlearning has demonstrated effectiveness in removing the influence of undesirable data (also known as forget data). Existing approaches typically assume full access to the forget dataset, overlooking two key…

Computation and Language · Computer Science 2025-09-19 Linxi Xie , Xin Teng , Shichang Ke , Hongyi Wen , Shengjie Wang

This work analyses the text memorization behavior of large language models (LLMs) when subjected to nucleus sampling. Stochastic decoding methods like nucleus sampling are typically applied to overcome issues such as monotonous and…

Computation and Language · Computer Science 2024-08-30 Luka Borec , Philipp Sadler , David Schlangen

While the Large Language Models (LLMs) dominate a majority of language understanding tasks, previous work shows that some of these results are supported by modelling spurious correlations of training datasets. Authors commonly assess model…

Computation and Language · Computer Science 2024-02-07 Lukáš Mikula , Michal Štefánik , Marek Petrovič , Petr Sojka

Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to appropriately adapt responses to the certainty of the retrieved information. It is a…

Computation and Language · Computer Science 2026-05-11 Behzad Shayegh , Mohamed Osama Ahmed , Fred Tung , Leo Feng

This paper introduces a novel method, referred to as "hashing", which involves masking potentially bias-inducing words in large language models (LLMs) with hash-like meaningless identifiers to reduce cognitive biases and reliance on…

Computation and Language · Computer Science 2025-06-12 Milena Chadimová , Eduard Jurášek , Tomáš Kliegr

We explore uncertainty quantification in large language models (LLMs), with the goal to identify when uncertainty in responses given a query is large. We simultaneously consider both epistemic and aleatoric uncertainties, where the former…

Machine Learning · Computer Science 2024-07-18 Yasin Abbasi Yadkori , Ilja Kuzborskij , András György , Csaba Szepesvári

Learning from negative samples holds great promise for improving Large Language Model (LLM) reasoning capability, yet existing methods treat all incorrect responses as equally informative, overlooking the crucial role of sample quality. To…

Machine Learning · Computer Science 2026-02-05 Zixiang Di , Jinyi Han , Shuo Zhang , Ying Liao , Zhi Li , Xiaofeng Ji , Yongqi Wang , Zheming Yang , Ming Gao , Bingdong Li , Jie Wang
‹ Prev 1 8 9 10 Next ›