English
Related papers

Related papers: Improving Causal Interventions in Amnesic Probing …

200 papers

Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, in complex tasks, GRPO frequently…

Artificial Intelligence · Computer Science 2026-05-08 Langlin Huang , Chengsong Huang , Jinyuan Li , Donghong Cai , Yuyi Yang , Jiaxin Huang

While neural networks have been successfully applied to many natural language processing tasks, they come at the cost of interpretability. In this paper, we propose a general methodology to analyze and interpret decisions from a neural…

Computation and Language · Computer Science 2017-01-11 Jiwei Li , Will Monroe , Dan Jurafsky

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

To measure how well pretrained representations encode some linguistic property, it is common to use accuracy of a probe, i.e. a classifier trained to predict the property from the representations. Despite widespread adoption of probes,…

Computation and Language · Computer Science 2020-03-30 Elena Voita , Ivan Titov

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Computation and Language · Computer Science 2021-12-14 Nicola De Cao , Leon Schmid , Dieuwke Hupkes , Ivan Titov

Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time…

Robotics · Computer Science 2017-03-22 Aviv Tamar , Garrett Thomas , Tianhao Zhang , Sergey Levine , Pieter Abbeel

When language models (LMs) are trained to forget (or "unlearn'') a skill, how precisely does their behavior change? We study the behavior of transformer LMs in which tasks have been forgotten via fine-tuning on randomized labels. Such LMs…

Machine Learning · Computer Science 2024-09-05 Eric Zhang , Leshem Chosen , Jacob Andreas

Deep supervised learning has achieved remarkable success across a wide range of tasks, yet it remains susceptible to overfitting when confronted with noisy labels. To address this issue, noise-robust loss functions offer an effective…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Xichen Ye , Yifan Wu , Yiqi Wang , Xiaoqiang Li , Weizhong Zhang , Yifan Chen

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

Computation and Language · Computer Science 2025-11-11 Myeongseob Ko , Nikhil Reddy Billa , Adam Nguyen , Charles Fleming , Ming Jin , Ruoxi Jia

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Computation and Language · Computer Science 2026-05-19 Xiaoyu Xu , Xiang Yue , Yang Liu , Qingqing Ye , Huadi Zheng , Peizhao Hu , Minxin Du , Haibo Hu

We investigate how agents built on pretrained large language models (LLMs) can learn target classification functions from labeled examples without parameter updates. While conventional approaches like fine-tuning are often costly,…

Computation and Language · Computer Science 2026-05-06 Jackson Hassell , Dan Zhang , Hannah Kim , Tom Mitchell , Estevam Hruschka

Despite an ever growing number of word representation models introduced for a large number of languages, there is a lack of a standardized technique to provide insights into what is captured by these models. Such insights would help the…

Computation and Language · Computer Science 2019-12-12 Gözde Gül Şahin , Clara Vania , Ilia Kuznetsov , Iryna Gurevych

Information-theoretic measures have been widely adopted in the design of features for learning and decision problems. Inspired by this, we look at the relationship between i) a weak form of information loss in the Shannon sense and ii) the…

Machine Learning · Computer Science 2022-01-03 Jorge F. Silva , Felipe Tobar , Mario Vicuña , Felipe Cordova

Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learning a reward function…

Large Language Models (LLMs) can achieve inflated scores on multiple-choice tasks by exploiting inherent biases in option positions or labels, rather than demonstrating genuine understanding. This study introduces SCOPE, an evaluation…

Computation and Language · Computer Science 2025-08-05 Wonjun Jeong , Dongseok Kim , Taegkeun Whangbo

Large Language Models (LLMs) excel at various tasks, including solving math word problems (MWPs), but struggle with real-world problems containing irrelevant information. To address this, we propose a prompting framework that generates…

Computation and Language · Computer Science 2025-09-17 Ujjwala Anantheswaran , Himanshu Gupta , Kevin Scaria , Shreyas Verma , Chitta Baral , Swaroop Mishra

We introduce a novel, closed-form approach for selective unlearning in multimodal models, specifically targeting pretrained models such as CLIP. Our method leverages nullspace projection to erase the target class information embedded in the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Ashish Mishra , Tarun Kumar , Gyanaranjan Nayak , Arpit Shah , Suparna Bhattacharya , Martin Foltin

Inference is a versatile tool that underlies scientific discovery, machine learning, and everyday decision-making: it describes how an agent updates a probability distribution as partial information is acquired from multiple measurements,…

Statistical Mechanics · Physics 2026-01-27 Nathan Shettell , Alexia Auffèves

As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become paramount. Recent work has explored sparse autoencoders (SAEs)…

Computation and Language · Computer Science 2026-04-28 Tomer Ashuach , Dana Arad , Aaron Mueller , Martin Tutek , Yonatan Belinkov

Applying imitation learning (IL) is challenging to nonprehensile manipulation tasks of invisible objects with partial observations, such as excavating buried rocks. The demonstrator must make such complex action decisions as exploring to…

Robotics · Computer Science 2025-03-24 Hirotaka Tahara , Takamitsu Matsubara
‹ Prev 1 3 4 5 6 7 10 Next ›