paper-with-me

Papers

Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues

2023-07-13 · Wentao Deng, Jiahuan Pei, Zhaochun Ren, Zhumin Chen, Pengjie Ren

Answer selection in open-domain dialogues aims to select an accurate answer from candidates. Recent success of answer selection models hinges on training with large amounts of labeled data. However, collecting large-scale labeled data is labor-intensive and time-consuming. In this paper, we introduce the predicted intent labels to calibrate answer labels in a self-training paradigm. Specifically, we propose the intent-calibrated self-training (ICAST) to improve the quality of pseudo answer labels through the intent-calibrated answer selection paradigm, in which we employ pseudo intent labels to help improve pseudo answer labels. We carry out extensive experiments on two benchmark datasets with open-domain dialogues. The experimental results show that ICAST outperforms baselines consistently with 1%, 5% and 10% labeled data. Specifically, it improves 2.06% and 1.00% of F1 score on the two datasets, compared with the strongest baseline with only 5% labeled data.

📄 PDF Abstract BibTeX arXiv:2307.06703

Code (0)

등록된 구현이 없습니다.

Tasks

Answer Selection

Similar Papers 제목 키워드 기반

QAID: Question Answering Inspired Few-shot Intent Detection

2023-03-02 · Asaf Yehudai, Matan Vetzler, Yosi Mass, Koren Lazar 외

Intent detection with semantically similar fine-grained intents is a challenging task. To address it, we reformulate intent detection as a question-answering retrieval task by treating utterances and intent names as ques…

Intent DetectionQuestion AnsweringRetrieval

OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets

2026-07-02 · Rheeya Uppaal, Seungwoo Lyu, Selina Sung, Junjie Hu arxiv

Safe completion requires models to provide useful assistance without enabling harm, but this behavior is difficult to evaluate with isolated prompts. We introduce OpenSafeIntent, a benchmark of controlled prompt-sets tha…

Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning

2025-08-25 · Jungsuk Oh, Jay-Yoon Lee arxiv

Probabilistic decoding in Large Language Models (LLMs) often yields inconsistent outputs, particularly on complex or long-form questions. Self-Consistency (SC) mitigates this for short-form QA by majority voting over exa…

Human Uncertainty-Aware Data Selection and Automatic Labeling in Visual Question Answering

2025-10-13 · Jian Lan, Zhicheng Liu, Udo Schlegel, Raoyuan Zhao 외 arxiv

Large vision-language models (VLMs) achieve strong performance in Visual Question Answering but still rely heavily on supervised fine-tuning (SFT) with massive labeled datasets, which is costly due to human annotations. …

Visual Question Answering

IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering

2025-10-27 · Jieyong Kim, Maryam Amirizaniani, Soojin Yoon, Dongha Lee arxiv

Intent identification serves as the foundation for generating appropriate responses in personalized question answering (PQA). However, existing benchmarks evaluate only response quality or retrieval performance without d…

Question AnsweringAnswer Selection