English
Related papers

Related papers: Improving Factual Consistency Between a Response a…

200 papers

Sequence to sequence models attempt to capture the correlation between all the words in the input and output sequences. While this is quite useful for machine translation where the correlation among the words is indeed quite strong, it…

Computation and Language · Computer Science 2020-04-02 Gaurav Pandey , Dinesh Raghu , Sachindra Joshi

Despite significant progress has been achieved in text summarization, factual inconsistency in generated summaries still severely limits its practical applications. Among the key factors to ensure factual consistency, a reliable automatic…

Computation and Language · Computer Science 2021-09-09 Yuexiang Xie , Fei Sun , Yang Deng , Yaliang Li , Bolin Ding

Personalized generation models for a single subject have demonstrated remarkable effectiveness, highlighting their significant potential. However, when extended to multiple subjects, existing models often exhibit degraded performance,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Shulei Wang , Longhui Wei , Xin He , Jianbo Ouyang , Hui Lu , Zhou Zhao , Qi Tian

In the domain of Visual Question Answering (VQA), studies have shown improvement in users' mental model of the VQA system when they are exposed to examples of how these systems answer certain Image-Question (IQ) pairs. In this work, we show…

Computer Vision and Pattern Recognition · Computer Science 2021-10-19 Kamran Alipour , Arijit Ray , Xiao Lin , Michael Cogswell , Jurgen P. Schulze , Yi Yao , Giedrius T. Burachas

Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However,…

Artificial Intelligence · Computer Science 2025-11-12 Qianxi He , Qingyu Ren , Shanzhe Lei , Xuhong Wang , Yingchun Wang

Despite the recent advances in abstractive summarization systems, it is still difficult to determine whether a generated summary is factual consistent with the source text. To this end, the latest approach is to train a factual consistency…

Computation and Language · Computer Science 2022-05-05 Hwanhee Lee , Kang Min Yoo , Joonsuk Park , Hwaran Lee , Kyomin Jung

We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues…

Computation and Language · Computer Science 2019-06-17 Can Xu , Wei Wu , Chongyang Tao , Huang Hu , Matt Schuerman , Ying Wang

In multi-turn dialog, utterances do not always take the full form of sentences \cite{Carbonell1983DiscoursePA}, which naturally makes understanding the dialog context more difficult. However, it is essential to fully grasp the dialog…

Computation and Language · Computer Science 2020-12-15 Xiuying Chen , Zhi Cui , Jiayi Zhang , Chen Wei , Jianwei Cui , Bin Wang , Dongyan Zhao , Rui Yan

Mobile devices use language models to suggest words and phrases for use in text entry. Traditional language models are based on contextual word frequency in a static corpus of text. However, certain types of phrases, when offered to writers…

Computation and Language · Computer Science 2017-10-06 Kenneth C. Arnold , Kai-Wei Chang , Adam T. Kalai

Recent advances in large language models (LLMs) have demonstrated significant progress in performing complex tasks. While Reinforcement Learning from Human Feedback (RLHF) has been effective in aligning LLMs with human preferences, it is…

Machine Learning · Computer Science 2025-05-30 Chaoqi Wang , Zhuokai Zhao , Yibo Jiang , Zhaorun Chen , Chen Zhu , Yuxin Chen , Jiayi Liu , Lizhu Zhang , Xiangjun Fan , Hao Ma , Sinong Wang

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises others (e.g., harmlessness) due to the inherent conflicts…

Computation and Language · Computer Science 2025-04-16 Zhihao Xu , Yongqi Tong , Xin Zhang , Jun Zhou , Xiting Wang

Reward models (RMs) play a crucial role in reinforcement learning from human feedback (RLHF), aligning model behavior with human preferences. However, existing benchmarks for reward models show a weak correlation with the performance of…

Machine Learning · Computer Science 2025-05-20 Sunghwan Kim , Dongjin Kang , Taeyoon Kwon , Hyungjoo Chae , Dongha Lee , Jinyoung Yeo

We present a novel framework addressing a critical vulnerability in Large Language Models (LLMs): the prevalence of factual inaccuracies within intermediate reasoning steps despite correct final answers. This phenomenon poses substantial…

Computation and Language · Computer Science 2025-08-05 Rui Jiao , Yue Zhang , Jinku Li

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

Natural language generators for task-oriented dialog should be able to vary the style of the output utterance while still effectively realizing the system dialog actions and their associated semantics. While the use of neural generation for…

Computation and Language · Computer Science 2018-09-06 Shereen Oraby , Lena Reed , Sharath TS , Shubhangi Tandon , Marilyn Walker

Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited…

Computation and Language · Computer Science 2025-06-03 Mingda Chen , Yang Li , Karthik Padthe , Rulin Shao , Alicia Sun , Luke Zettlemoyer , Gargi Ghosh , Wen-tau Yih

How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human preferences over model outputs are used to train a reward model that assigns scalar values to responses. Because…

Artificial Intelligence · Computer Science 2026-05-11 Tiffany Horter , Andrew Markham , Niki Trigoni , Serena Booth

Neural generative models have become popular and achieved promising performance on short-text conversation tasks. They are generally trained to build a 1-to-1 mapping from the input post to its output response. However, a given post is…

Computation and Language · Computer Science 2019-02-22 Jun Gao , Wei Bi , Xiaojiang Liu , Junhui Li , Shuming Shi

Pretrained language models (LMs) are susceptible to generate text with nonfactual information. In this work, we measure and improve the factual accuracy of large-scale LMs for open-ended text generation. We design the FactualityPrompts test…

Computation and Language · Computer Science 2023-03-03 Nayeon Lee , Wei Ping , Peng Xu , Mostofa Patwary , Pascale Fung , Mohammad Shoeybi , Bryan Catanzaro

This paper explores an intriguing observation: fine-tuning a large language model (LLM) with responses generated by a LLM often yields better results than using responses generated by humans, particularly in reasoning tasks. We conduct an…

Computation and Language · Computer Science 2025-12-09 Xuan Ren , Biao Wu , Lingqiao Liu
‹ Prev 1 8 9 10 Next ›