English
Related papers

Related papers: Re3: Generating Longer Stories With Recursive Repr…

200 papers

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often leads to excessively verbose processes (in reasoning tasks) and…

Artificial Intelligence · Computer Science 2025-10-01 Gang Li , Yulei Qin , Xiaoyu Tan , Dingkang Yang , Yuchen Shi , Zihan Xu , Xiang Li , Xing Sun , Ke Li

This study investigates whether repeating questions within prompts influences the performance of large language models (LLMs). We hypothesize that reiterating a question within a single prompt might enhance the model's focus on key elements…

Computation and Language · Computer Science 2025-03-13 Sagi Shaier , Mario Sanz-Guerrero , Katharina von der Wense

Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even…

Computation and Language · Computer Science 2021-05-25 Han Wang , Yang Liu , Chenguang Zhu , Linjun Shou , Ming Gong , Yichong Xu , Michael Zeng

Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…

Computation and Language · Computer Science 2026-03-03 Yaorui Shi , Yuxin Chen , Siyuan Wang , Sihang Li , Hengxing Cai , Qi Gu , Xiang Wang , An Zhang

A classic tension exists between exact inference in a simple model and approximate inference in a complex model. The latter offers expressivity and thus accuracy, but the former provides coverage of the space, an important property for…

Machine Learning · Computer Science 2015-02-25 Jacob Steinhardt , Percy Liang

To enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs), we introduce a simple, yet general and effective prompting method, Re2, i.e., \textbf{Re}-\textbf{Re}ading the question as input. Unlike most…

Computation and Language · Computer Science 2024-11-20 Xiaohan Xu , Chongyang Tao , Tao Shen , Can Xu , Hongbo Xu , Guodong Long , Jian-guang Lou , Shuai Ma

Generating long-term texts such as novels using artificial intelligence has always been a challenge. A common approach is to use large language models (LLMs) to construct a hierarchical framework that first plans and then writes. Despite…

Computation and Language · Computer Science 2024-09-04 Lei Huang , Jiaming Guo , Guanhua He , Xishan Zhang , Rui Zhang , Shaohui Peng , Shaoli Liu , Tianshi Chen

Reading and repeatedly retelling a short story is a common and effective approach to learning the meanings and usages of target words. However, learners often struggle with comprehending, recalling, and retelling the story contexts of these…

Human-Computer Interaction · Computer Science 2024-05-27 Qiaoyi Chen , Siyu Liu , Kaihui Huang , Xingbo Wang , Xiaojuan Ma , Junkai Zhu , Zhenhui Peng

Conditional story generation is significant in human-machine interaction, particularly in producing stories with complex plots. While Large language models (LLMs) perform well on multiple NLP tasks, including story generation, it is…

Computation and Language · Computer Science 2023-10-25 Zhihua Wen , Zhiliang Tian , Wei Wu , Yuxin Yang , Yanqi Shi , Zhen Huang , Dongsheng Li

Recent text generation models are easy to generate relevant and fluent text for the given text, while lack of causal reasoning ability when we change some parts of the given text. Counterfactual story rewriting is a recently proposed task…

Computation and Language · Computer Science 2021-04-05 Changying Hao , Liang Pang , Yanyan Lan , Yan Wang , Jiafeng Guo , Xueqi Cheng

This paper addresses the challenge of comprehending very long contexts in Large Language Models (LLMs) by proposing a method that emulates Retrieval Augmented Generation (RAG) through specialized prompt engineering and chain-of-thought…

Computation and Language · Computer Science 2025-02-19 Joon Park , Kyohei Atarashi , Koh Takeuchi , Hisashi Kashima

Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted…

Computation and Language · Computer Science 2020-05-05 Ruiyi Zhang , Changyou Chen , Zhe Gan , Wenlin Wang , Dinghan Shen , Guoyin Wang , Zheng Wen , Lawrence Carin

Large pre-trained language models are capable of generating varied and fluent texts. Starting from the prompt, these models generate a narrative that can develop unpredictably. The existing methods of controllable text generation, which…

Computation and Language · Computer Science 2022-06-22 Sergey Vychegzhanin , Evgeny Kotelnikov

Pre-trained language models (PLMs) fail to generate long-form narrative text because they do not consider global structure. As a result, the generated texts are often incohesive, repetitive, or lack content. Recent work in story generation…

Computation and Language · Computer Science 2022-06-08 Yiping Jin , Vishakha Kadam , Dittaya Wanvarie

Recent advancements in self-attention neural network architectures have raised the bar for open-ended text generation. Yet, while current methods are capable of producing a coherent text which is several hundred words long, attaining…

Computation and Language · Computer Science 2020-12-09 Eyal Orbach , Yoav Goldberg

Automated story generation has been one of the long-standing challenges in NLP. Among all dimensions of stories, suspense is very common in human-written stories but relatively under-explored in AI-generated stories. While recent advances…

Computation and Language · Computer Science 2024-02-28 Kaige Xie , Mark Riedl

In recent years, the generation of conversation content based on deep neural networks has attracted many researchers. However, traditional neural language models tend to generate general replies, lacking logical and emotional factors. This…

Computation and Language · Computer Science 2019-04-18 Jia Li , Xiao Sun , Xing Wei , Changliang Li , Jianhua Tao

Standard language models generate text by selecting tokens from a fixed, finite, and standalone vocabulary. We introduce a novel method that selects context-aware phrases from a collection of supporting documents. One of the most…

Computation and Language · Computer Science 2024-03-19 Bowen Cao , Deng Cai , Leyang Cui , Xuxin Cheng , Wei Bi , Yuexian Zou , Shuming Shi

Query rewriting plays a vital role in enhancing conversational search by transforming context-dependent user queries into standalone forms. Existing approaches primarily leverage human-rewritten queries as labels to train query rewriting…

Human-Computer Interaction · Computer Science 2023-10-19 Fanghua Ye , Meng Fang , Shenghui Li , Emine Yilmaz

Existing large language models have to run K times to generate a sequence of K tokens. In this paper, we present RecycleGPT, a generative language model with fast decoding speed by recycling pre-generated model states without running the…

Computation and Language · Computer Science 2024-05-24 Yufan Jiang , Qiaozhi He , Xiaomin Zhuang , Zhihua Wu , Kunpeng Wang , Wenlai Zhao , Guangwen Yang