English
Related papers

Related papers: Qr-Hint: Actionable Hints Towards Correcting Wrong…

200 papers

Click-Through Rate (CTR) prediction, a core task in recommendation systems, estimates user click likelihood using historical behavioral data. Modeling user behavior sequences as text to leverage Language Models (LMs) for this task has…

Computation and Language · Computer Science 2025-08-06 Zixuan Li , Binzong Geng , Jing Xiong , Yong He , Yuxuan Hu , Jian Chen , Dingwei Chen , Xiyu Chang , Liang Zhang , Linjian Mo , Chengming Li , Chuan Yuan , Zhenan Sun

LLMs are reshaping education, with students increasingly relying on them for learning. Implemented using general-purpose models, these systems are likely to give away the answers, potentially undermining conceptual understanding and…

Human-Computer Interaction · Computer Science 2026-02-23 Anubhav Jangra , Smaranda Muresan

Reinforcement learning has become a powerful approach for enhancing large language model reasoning, but faces a fundamental dilemma: training on easy problems can cause overfitting and pass@k degradation, while training on hard problems…

Machine Learning · Computer Science 2026-05-04 Yangyi Fang , Jiaye Lin , Xiaoliang Fu , Cong Qin , Haolin Shi

In modern search systems, search engines often suggest relevant queries to users through various panels or components, helping refine their information needs. Traditionally, these recommendations heavily rely on historical search logs to…

Information Retrieval · Computer Science 2025-07-08 Erxue Min , Hsiu-Yuan Huang , Xihong Yang , Min Yang , Xin Jia , Yunfang Wu , Hengyi Cai , Junfeng Wang , Shuaiqiang Wang , Dawei Yin

Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from real user questions and expected answers. This study proposes…

Computation and Language · Computer Science 2025-02-14 Yang Li , Mingxuan Luo , Yeyun Gong , Chen Lin , Jian Jiao , Yi Liu , Kaili Huang

Small language models (SLMs) often struggle with complex mathematical reasoning due to limited capacity to maintain long chains of intermediate steps and to recover from early errors. We address this challenge by introducing a hint-assisted…

Artificial Intelligence · Computer Science 2026-04-15 Jawad Hossain , Xiangyu Guo , Jiawei Zhou , Chong Liu

Evaluating LLM-based agents remains challenging because identifying meaningful failure cases often requires substantial human effort to design realistic test scenarios. Prior works primarily focus on automatically discovering agent failures…

Computation and Language · Computer Science 2026-05-19 Yunan Lu , Luigi Liu , Omar Yahia , Arpit Sharma , Zhou Yu

Intent classification is an important component of a functional Information Retrieval ecosystem. Many current approaches to intent classification, typically framed as a classification problem, can be problematic as intents are often hard to…

Information Retrieval · Computer Science 2025-05-27 Arjun Bhalla , Qi Huang

Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not which intermediate actions caused the outcome or how they should be corrected. Recent methods…

Machine Learning · Computer Science 2026-05-19 Woongyeng Yeo , Yumin Choi , Taekyung Ki , Sung Ju Hwang

This work introduces the Query/Hit (Q/H) learning model. The setup consists of two agents. One agent, Alice, has access to a streaming source, while the other, Bob, does not have direct access to the source. Communication occurs through…

Information Theory · Computer Science 2025-02-04 Mahshad Shariatnasab , Stefano Rini , Farhad Shirani , S. Sitharama Iyengar

Conversational search seeks to retrieve relevant passages for the given questions in conversational question answering. Conversational Query Reformulation (CQR) improves conversational search by refining the original queries into…

Computation and Language · Computer Science 2025-05-16 Jeonghyun Park , Hwanhee Lee

We propose a model for errors in sung queries, a variant of the hidden Markov model (HMM). This is a solution to the problem of identifying the degree of similarity between a (typically error-laden) sung query and a potential target in a…

Artificial Intelligence · Computer Science 2011-07-04 W. P. Birmingham , C. J. Meek

Keyword search against structured databases has become a popular topic of investigation, since many users find structured queries too hard to express, and enjoy the freedom of a ``Google-like'' query box into which search terms can be…

Databases · Computer Science 2009-09-15 Arnab Nandi , H V Jagadish

Text-to-SQL generation bridges the gap between natural language and databases, enabling users to query data without requiring SQL expertise. While large language models (LLMs) have significantly advanced the field, challenges remain in…

Machine Learning · Computer Science 2025-12-18 Ganesh Parab , Zishan Ahmad , Dagnachew Birru

Existing work on vision and language navigation mainly relies on navigation-related losses to establish the connection between vision and language modalities, neglecting aspects of helping the navigation agent build a deep understanding of…

Computation and Language · Computer Science 2024-02-06 Yue Zhang , Quan Guo , Parisa Kordjamshidi

Abstract. When writing an academic paper, researchers often spend considerable time reviewing and summarizing papers to extract relevant citations and data to compose the Introduction and Related Work sections. To address this problem, we…

Information Retrieval · Computer Science 2023-06-22 Juan Ramirez-Orta , Eduardo Xamena , Ana Maguitman , Axel J. Soto , Flavia P. Zanoto , Evangelos Milios

Joint planning through language-based interactions is a key area of human-AI teaming. Planning problems in the open world often involve various aspects of incomplete information and unknowns, e.g., objects involved, human goals/intents --…

Artificial Intelligence · Computer Science 2026-05-05 Zeyu Fang , Mahdi Imani , Tian Lan

Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods like GRPO often fail when task difficulty exceeds the…

Machine Learning · Computer Science 2025-10-13 Xinyi Wang , Jinyi Han , Zishang Jiang , Tingyun Li , Jiaqing Liang , Sihang Jiang , Zhaoqian Dai , Shuguang Ma , Fei Yu , Yanghua Xiao

Traditional data systems require specialized technical skills where users need to understand the data organization and write precise queries to access data. Therefore, novice users who lack technical expertise face hurdles in perusing and…

Human-Computer Interaction · Computer Science 2021-01-05 Anna Fariha , Lucy Cousins , Narges Mahyar , Alexandra Meliou

Query auto completion (QAC) systems are a standard part of search engines in industry, helping users formulate their query. Such systems update their suggestions after the user types each character, predicting the user's intent using…

Computation and Language · Computer Science 2018-05-10 Nicolas Fiorini , Zhiyong Lu