paper-with-me

홈 › Papers

Atomic Self-Consistency for Better Long Form Generations

2024-05-21 · Raghuveer Thirukovalluru, Yukun Huang, Bhuwan Dhingra

Recent work has aimed to improve LLM generations by filtering out hallucinations, thereby improving the precision of the information in responses. Correctness of a long-form response, however, also depends on the recall of multiple pieces of information relevant to the question. In this paper, we introduce Atomic Self-Consistency (ASC), a technique for improving the recall of relevant information in an LLM response. ASC follows recent work, Universal Self-Consistency (USC) in using multiple stochastic samples from an LLM to improve the long-form response. Unlike USC which only focuses on selecting the best single generation, ASC picks authentic subparts from the samples and merges them into a superior composite answer. Through extensive experiments and ablations, we show that merging relevant subparts of multiple samples performs significantly better than picking a single sample. ASC demonstrates significant gains over USC on multiple factoids and open-ended QA datasets - ASQA, QAMPARI, QUEST, ELI5 with ChatGPT and Llama2. Our analysis also reveals untapped potential for enhancing long-form generations using approach of merging multiple samples.

📄 PDF Abstract BibTeX arXiv:2405.13131

Code (0)

등록된 구현이 없습니다.

Tasks

Form

Similar Papers 제목 키워드 기반

Learning Anatomically Consistent Embedding for Chest Radiography

2023-12-01 · Ziyu Zhou, Haozhe Luo, Jiaxuan Pang, Xiaowei Ding 외

Self-supervised learning (SSL) approaches have recently shown substantial success in learning visual representations from unannotated images. Compared with photographic images, medical images acquired with the same imagi…

AnatomyMedical Image AnalysisSelf-Supervised Learning

Atomic Consistency Preference Optimization for Long-Form Question Answering

2025-05-14 · Jingfeng Chen, Raghuveer Thirukovalluru, Junlin Wang, Kaiwei Luo 외

Large Language Models (LLMs) frequently produce factoid hallucinations - plausible yet incorrect answers. A common mitigation strategy is model alignment, which improves factual accuracy by training on curated factual an…

FormLong Form Question AnsweringQuestion Answering

MambaControl: Anatomy Graph-Enhanced Mamba ControlNet with Fourier Refinement for Diffusion-Based Disease Trajectory Prediction

2025-05-15 · Hao Yang, Tao Tan, Shuai Tan, Weiqin Yang 외

Modelling disease progression in precision medicine requires capturing complex spatio-temporal dynamics while preserving anatomical integrity. Existing methods often struggle with longitudinal dependencies and structural…

AnatomyDisease PredictionMambaPrediction+2

ASCON: Anatomy-aware Supervised Contrastive Learning Framework for Low-dose CT Denoising

2023-07-23 · Zhihao Chen, Qi Gao, Yi Zhang, Hongming Shan

While various deep learning methods have been proposed for low-dose computed tomography (CT) denoising, most of them leverage the normal-dose CT images as the ground-truth to supervise the denoising process. These method…

AnatomyComputed Tomography (CT)Contrastive LearningDenoising

AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Images

2025-04-15 · Yihang Liu, Lianghua He, Ying Wen, Longzhen Yang 외

Current self-supervised methods, such as contrastive learning, predominantly focus on global discrimination, neglecting the critical fine-grained anatomical details required for accurate radiographic analysis. To address…

AnatomyAnomaly DetectionContrastive LearningMulti-Label Classification+2