English
Related papers

Related papers: {\dag}DAGGER: Distractor-Aware Graph Generation fo…

200 papers

Distractor generation (DG) remains a labor-intensive task that still significantly depends on domain experts. The task focuses on generating plausible yet incorrect options, known as distractors, for multiple-choice questions. A reliable…

Computation and Language · Computer Science 2026-04-21 Elaf Alhazmi , Quan Z. Sheng , Wei Emma Zhang

In this paper, we tackle the task of distractor generation (DG) for multiple-choice questions. Our study introduces two key designs. First, we propose \textit{retrieval augmented pretraining}, which involves refining the language model…

Computation and Language · Computer Science 2024-06-21 Han-Cheng Yu , Yu-An Shih , Kin-Man Law , Kai-Yu Hsieh , Yu-Chen Cheng , Hsin-Chih Ho , Zih-An Lin , Wen-Chuan Hsu , Yao-Chung Fan

Graph-based Retrieval-Augmented Generation (GraphRAG) has become the important paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing approaches are constrained by their reliance on high-quality…

Computation and Language · Computer Science 2026-01-07 Xiaojun Wu , Cehao Yang , Xueyuan Lin , Chengjin Xu , Xuhui Jiang , Yuanliang Sun , Hui Xiong , Jia Li , Jian Guo

We introduce Grade School Math with Distracting Context (GSM-DC), a synthetic benchmark to evaluate Large Language Models' (LLMs) reasoning robustness against systematically controlled irrelevant context (IC). GSM-DC constructs symbolic…

Computation and Language · Computer Science 2025-09-23 Minglai Yang , Ethan Huang , Liang Zhang , Mihai Surdeanu , William Wang , Liangming Pan

This study investigates the in-context learning capabilities of various decoder-only transformer-based language models with different model sizes and training data, including GPT2, SmolLM2, OpenELM, TinyLlama, Stable LM, and Gemma 2. We…

Computation and Language · Computer Science 2025-02-24 Yen-Che Hsiao , Abhishek Dutta

Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries. This phenomenon arises from LLMs' working memory constraints, which result in their…

Artificial Intelligence · Computer Science 2025-10-01 Rongzheng Wang , Shuang Liang , Qizhi Chen , Yihong Huang , Muquan Li , Yizhuo Ma , Dongyang Zhang , Ke Qin , Man-Fai Leung

Large reasoning models (LRMs) achieve strong mathematical reasoning performance in English, but remain much less reliable in many low- and medium-resource languages. This gap is often explained as a failure to understand non-English problem…

Computation and Language · Computer Science 2026-05-28 Jiaqiao Zhang , Zhoujun Li , Raoyuan Zhao , Jian Lan , Thomas Seidl , Michael A. Hedderich , Hinrich Schütze , Yihong Liu

Large Reasoning Models (LRMs) have demonstrated strong performance by producing extended Chain-of-Thought (CoT) traces before answering. However, this paradigm often induces over-reasoning: redundant calculations and circular…

Artificial Intelligence · Computer Science 2026-03-10 Siyi Li , Jiajun Shi , Shiwen Ni , Ge Zhang , Shuaimin Li , Shijian Wang , Zhoufutu Wen , Yizhi Li , Hamid Alinejad-Rokny , Jiaheng Liu , Min Yang , Wenhao Huang

Chain-of-thought (CoT) reasoning boosts large language models' (LLMs) performance on complex tasks but faces two key limitations: a lack of reliability when solely relying on LLM-generated reasoning chains and lower reasoning performance…

Computation and Language · Computer Science 2025-09-11 Feiyang Li , Peng Fang , Zhan Shi , Arijit Khan , Fang Wang , Weihao Wang , Xin Zhang , Yongjian Cui

High-quality distractors are crucial to both the assessment and pedagogical value of multiple-choice questions (MCQs), where manually crafting ones that anticipate knowledge deficiencies or misconceptions among real students is difficult.…

Computation and Language · Computer Science 2024-10-10 Nigel Fernandez , Alexander Scarlatos , Wanyong Feng , Simon Woodhead , Andrew Lan

The method of training language models based on domain datasets has obtained significant achievements in the task of generating scientific paper abstracts. However, such models face problems of generalization and expensive training costs.…

Computation and Language · Computer Science 2024-03-27 Xinyu Ning , Yutong Zhao , Yitong Liu , Hongwen Yang

Large Language Models (LLMs) demonstrate strong performance on mathematical problems when prompted with Chain-of-Thought (CoT), yet it remains unclear whether this success stems from search, rote procedures, or rule-consistent reasoning. To…

Artificial Intelligence · Computer Science 2026-03-03 Yuanhe Zhang , Ilja Kuzborskij , Jason D. Lee , Chenlei Leng , Fanghui Liu

Retrieval-augmented generation (RAG) often falls short when retrieved context includes confusing semi-relevant passages, or when answering questions require deep contextual understanding and reasoning. We propose an efficient fine-tuning…

Computation and Language · Computer Science 2025-07-28 Mohammad Kachuee , Teja Gollapudi , Minseok Kim , Yin Huang , Kai Sun , Xiao Yang , Jiaqi Wang , Nirav Shah , Yue Liu , Aaron Colak , Anuj Kumar , Wen-tau Yih , Xin Luna Dong

Graph combinatorial optimization (GCO) problems are central to domains like logistics and bioinformatics. While traditional solvers dominate, large language models (LLMs) offer new possibilities for structured reasoning, yet struggle with…

Machine Learning · Computer Science 2025-06-13 Zixiao Huang , Lifeng Guo , Wenhao Li , Junjie Sheng , Chuyun Shen , Haosheng Chen , Bo Jin , Changhong Lu , Xiangfeng Wang

Evaluating generative models with open-ended generation is challenging due to inconsistencies in response formats. Multiple-choice (MC) evaluation mitigates this issue, but generating high-quality distractors is time-consuming and…

Computation and Language · Computer Science 2025-06-16 Grace Byun , Jinho D. Choi

In this paper, we investigate the following two limitations for the existing distractor generation (DG) methods. First, the quality of the existing DG methods are still far from practical use. There is still room for DG quality improvement.…

Computation and Language · Computer Science 2020-10-13 Ho-Lam Chung , Ying-Hong Chan , Yao-Chung Fan

Retrieval-Augmented Generation (RAG) is a framework for grounding Large Language Models (LLMs) in external, up-to-date information. However, recent advancements in context window size allow LLMs to process inputs of up to 128K tokens or…

Machine Learning · Computer Science 2026-02-26 Seongwoong Shim , Myunsoo Kim , Jae Hyeon Cho , Byung-Jun Lee

Graph Retrieval Augmented Generation (GraphRAG) has garnered increasing recognition for its potential to enhance large language models (LLMs) by structurally organizing domain-specific corpora and facilitating complex reasoning. However,…

Computation and Language · Computer Science 2025-06-23 Yilin Xiao , Junnan Dong , Chuang Zhou , Su Dong , Qian-wen Zhang , Di Yin , Xing Sun , Xiao Huang

Reasoning models have demonstrated impressive performance on difficult tasks that traditional language models struggle at. However, many are plagued with the problem of overthinking--generating large amounts of unnecessary tokens which…

Computation and Language · Computer Science 2025-04-21 Xiao Pu , Michael Saxon , Wenyue Hua , William Yang Wang

Multiple-choice VQA has drawn increasing attention from researchers and end-users recently. As the demand for automatically constructing large-scale multiple-choice VQA data grows, we introduce a novel task called textual Distractors…

Computer Vision and Pattern Recognition · Computer Science 2022-04-20 Jiaying Lu , Xin Ye , Yi Ren , Yezhou Yang
‹ Prev 1 2 3 10 Next ›