English
Related papers

Related papers: Contrastive Perplexity for Controlled Generation: …

200 papers

Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and…

Computation and Language · Computer Science 2023-10-17 Chak Tou Leong , Yi Cheng , Jiashuo Wang , Jian Wang , Wenjie Li

The need for interpretability in deep learning has driven interest in counterfactual explanations, which identify minimal changes to an instance that change a model's prediction. Current counterfactual (CF) generation methods require…

Computation and Language · Computer Science 2025-12-11 Van Bach Nguyen , Christin Seifert , Jörg Schlötterer

Large language models (LLMs) tend to inadequately integrate input context during text generation, relying excessively on encoded prior knowledge in model parameters, potentially resulting in generated text with factual inconsistencies or…

Computation and Language · Computer Science 2024-05-07 Zheng Zhao , Emilio Monti , Jens Lehmann , Haytham Assem

The deployment of large language models (LLMs) faces considerable challenges concerning resource constraints and inference efficiency. Recent research has increasingly focused on smaller, task-specific models enhanced by distilling…

Computation and Language · Computer Science 2024-09-20 Wei Wang , Zhaowei Li , Qi Xu , Yiqing Cai , Hang Song , Qi Qi , Ran Zhou , Zhida Huang , Tao Wang , Li Xiao

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation,…

Computation and Language · Computer Science 2023-06-07 Chujie Zheng , Pei Ke , Zheng Zhang , Minlie Huang

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

With adversarial or otherwise normal prompts, existing large language models (LLM) can be pushed to generate toxic discourses. One way to reduce the risk of LLMs generating undesired discourses is to alter the training of the LLM. This can…

Computation and Language · Computer Science 2023-02-28 Meng Cao , Mehdi Fatemi , Jackie Chi Kit Cheung , Samira Shabanian

Large language models (LLMs) are trained on huge amounts of textual data, and concerns have been raised that the limits of such data may soon be reached. A potential solution is to train on synthetic data sampled from LLMs. In this work, we…

Computation and Language · Computer Science 2025-10-10 Jannek Ulm , Kevin Du , Vésteinn Snæbjarnarson

A common approach for testing fairness issues in text-based classifiers is through the use of counterfactuals: does the classifier output change if a sensitive attribute in the input is changed? Existing counterfactual generation methods…

Computation and Language · Computer Science 2022-06-29 Zee Fryer , Vera Axelrod , Ben Packer , Alex Beutel , Jilin Chen , Kellie Webster

Large language models (LLMs) are becoming increasingly important for machine learning applications. However, it can be challenging to align LLMs with our intent, particularly when we want to generate content that is preferable over others…

Computation and Language · Computer Science 2024-04-09 Xiang Gao , Kamalika Das

Recently, contrastive learning has been shown to be effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. It aims to pull close positive examples to enhance the alignment while push apart…

Computation and Language · Computer Science 2022-05-03 Kun Zhou , Beichen Zhang , Wayne Xin Zhao , Ji-Rong Wen

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Computation and Language · Computer Science 2026-03-05 Yuxiao Lu , Lin Xu , Yang Sun , Wenjun Li , Jie Shi

Decoding from the output distributions of large language models to produce high-quality text is a complex challenge in language modeling. Various approaches, such as beam search, sampling with temperature, $k-$sampling, nucleus…

Computation and Language · Computer Science 2024-10-22 Esteban Garces Arias , Julian Rodemann , Meimingwei Li , Christian Heumann , Matthias Aßenmacher

Existing approaches for Large language model (LLM) detoxification generally rely on training on large-scale non-toxic or human-annotated preference data, designing prompts to instruct the LLM to generate safe content, or modifying the model…

Computation and Language · Computer Science 2025-06-03 Yuanhe Tian , Mingjie Deng , Guoqing Jin , Yan Song

Automatic counterspeech generation methods have been developed to assist efforts in combating hate speech. Existing research focuses on generating counterspeech with linguistic attributes such as being polite, informative, and…

Computation and Language · Computer Science 2024-10-02 Lingzi Hong , Pengcheng Luo , Eduardo Blanco , Xiaoying Song

Recent breakthroughs in Large Language Models (LLMs) have revealed remarkable generative capabilities and emerging self-regulatory mechanisms, including self-correction and self-rewarding. However, current detoxification techniques rarely…

Computation and Language · Computer Science 2026-01-21 Kaituo Zhang , Zhimeng Jiang , Na Zou

Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application. In this paper, we conduct extensive experiments to study this phenomenon. We analyze the impact of…

Computation and Language · Computer Science 2022-03-08 Canwen Xu , Zexue He , Zhankui He , Julian McAuley

Fine-tuning large language models (LLMs) typically relies on producing large sets of input-output pairs. Yet for a given question, there can be many valid outputs. In practice, these outputs are often derived by distilling knowledge from…

Computation and Language · Computer Science 2025-08-28 Xuan Ren , Qi Chen , Lingqiao Liu

Large Language Models (LLMs) are powerful text generators, yet they can produce toxic or harmful content even when given seemingly harmless prompts. This presents a serious safety challenge and can cause real-world harm. Toxicity is often…

Computation and Language · Computer Science 2026-02-09 Himanshu Singh , Ziwei Xu , A. V. Subramanyam , Mohan Kankanhalli

Pre-trained language models (LMs) store knowledge in their parameters and can generate informative responses when used in conversational systems. However, LMs suffer from the problem of "hallucination:" they may generate plausible-looking…

Computation and Language · Computer Science 2022-12-21 Weiwei Sun , Zhengliang Shi , Shen Gao , Pengjie Ren , Maarten de Rijke , Zhaochun Ren
‹ Prev 1 2 3 10 Next ›