English
Related papers

Related papers: Distributional Surgery for Language Model Activati…

200 papers

Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…

Computation and Language · Computer Science 2021-09-22 Ramon Sanabria , Hao Tang , Sharon Goldwater

Large Language Models (LLMs) have demonstrated a powerful ability for text generation. However, achieving optimal results with a given prompt or instruction can be challenging, especially for billion-sized models. Additionally, undesired…

Computation and Language · Computer Science 2024-10-07 Lifu Tu , Semih Yavuz , Jin Qu , Jiacheng Xu , Rui Meng , Caiming Xiong , Yingbo Zhou

This research explores strategies for steering the output of large language models (LLMs) towards specific styles, such as sentiment, emotion, or writing style, by adding style vectors to the activations of hidden layers during text…

Computation and Language · Computer Science 2024-02-05 Kai Konen , Sophie Jentzsch , Diaoulé Diallo , Peer Schütt , Oliver Bensch , Roxanne El Baff , Dominik Opitz , Tobias Hecking

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…

Computation and Language · Computer Science 2020-06-22 Jasmijn Bastings , Wilker Aziz , Ivan Titov

Diffusion models have demonstrated remarkable capability in generating high-quality visual content from textual descriptions. However, since these models are trained on large-scale internet data, they inevitably learn undesirable concepts,…

Machine Learning · Computer Science 2025-02-18 Anh Bui , Khanh Doan , Trung Le , Paul Montague , Tamas Abraham , Dinh Phung

Semantic control entails steering LM generations towards satisfying subtle non-lexical constraints, e.g., toxicity, sentiment, or politeness, attributes that can be captured by a sequence-level verifier. It can thus be viewed as sampling…

Machine Learning · Computer Science 2025-05-06 Kareem Ahmed , Catarina G Belem , Padhraic Smyth , Sameer Singh

The rise of emergence of social media platforms has fundamentally altered how people communicate, and among the results of these developments is an increase in online use of abusive content. Therefore, automatically detecting this content…

Computation and Language · Computer Science 2023-02-20 Khouloud Mnassri , Praboda Rajapaksha , Reza Farahbakhsh , Noel Crespi

Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, researchers hoping…

Computation and Language · Computer Science 2023-06-02 Carolina Zheng , Claudia Shi , Keyon Vafa , Amir Feder , David M. Blei

Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior collapse. The former arises from the fact that only the last…

Machine Learning · Computer Science 2021-06-17 Xianghong Fang , Haoli Bai , Zenglin Xu , Michael Lyu , Irwin King

This paper describes a novel study on using `Attention Mask' input in transformers and using this approach for detecting offensive content in both English and Persian languages. The paper's principal focus is to suggest a methodology to…

Computation and Language · Computer Science 2021-10-12 Peyman Alavi , Pouria Nikvand , Mehrnoush Shamsfard

Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine…

Computation and Language · Computer Science 2024-10-04 Minseok Choi , Kyunghyun Min , Jaegul Choo

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$% of diffusion models' parameters, all contained in…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Łukasz Staniszewski , Bartosz Cywiński , Franziska Boenisch , Kamil Deja , Adam Dziedzic

Satirical news is considered to be entertainment, but it is potentially deceptive and harmful. Despite the embedded genre in the article, not everyone can recognize the satirical cues and therefore believe the news as true news. We observe…

Computation and Language · Computer Science 2017-09-06 Fan Yang , Arjun Mukherjee , Eduard Dragut

As open-ended human-chatbot interaction becomes commonplace, sensitive content detection gains importance. In this work, we propose a two stage semi-supervised approach to bootstrap large-scale data for automatic sensitive language…

Computation and Language · Computer Science 2018-12-03 Chandra Khatri , Behnam Hedayatnia , Rahul Goel , Anushree Venkatesh , Raefer Gabriel , Arindam Mandal

Due to the subtleness, implicity, and different possible interpretations perceived by different people, detecting undesirable content from text is a nuanced difficulty. It is a long-known risk that language models (LMs), once trained on…

Computation and Language · Computer Science 2022-05-26 Yau-Shian Wang , Yingshan Chang

Despite the impressive generative capabilities of text-to-image (T2I) diffusion models, they remain vulnerable to generating inappropriate content, especially when confronted with implicit sexual prompts. Unlike explicit harmful prompts,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-20 Yitong Sun , Yao Huang , Ruochen Zhang , Huanran Chen , Shouwei Ruan , Ranjie Duan , Xingxing Wei

Recent studies have shown that generative language models often reflect and amplify societal biases in their outputs. However, these studies frequently conflate observed biases with other task-specific shortcomings, such as comprehension…

Computation and Language · Computer Science 2024-12-17 Akshita Jha , Sanchit Kabra , Chandan K. Reddy

Denoising diffusion probabilistic models have recently received much research attention since they outperform alternative approaches, such as GANs, and currently provide state-of-the-art generative performance. The superior performance of…

Computer Vision and Pattern Recognition · Computer Science 2022-03-17 Dmitry Baranchuk , Ivan Rubachev , Andrey Voynov , Valentin Khrulkov , Artem Babenko

Recent computational approaches for combating online hate speech involve the automatic generation of counter narratives by adapting Pretrained Transformer-based Language Models (PLMs) with human-curated data. This process, however, can…

Computation and Language · Computer Science 2023-09-06 Helena Bonaldi , Giuseppe Attanasio , Debora Nozza , Marco Guerini

WARNING: This paper contains examples of offensive materials. To address the proliferation of toxic content on social media, we introduce SMARTER, we introduce SMARTER, a data-efficient two-stage framework for explainable content moderation…

Computation and Language · Computer Science 2026-04-23 Huy Nghiem , Advik Sachdeva , Hal Daumé
‹ Prev 1 3 4 5 6 7 10 Next ›