English
Related papers

Related papers: FABLE: Fine-grained Fact Anchoring for Unstructure…

200 papers

Large language models may encounter factual knowledge during pre-training yet fail to reliably use that knowledge after fine-tuning. Despite growing empirical evidence that MLP layers store factual associations and fine-tuning affects…

Machine Learning · Computer Science 2026-05-19 Ruichen Xu , Kexin Chen

Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we…

Computation and Language · Computer Science 2021-09-23 Dheeraj Mekala , Varun Gangal , Jingbo Shang

Generative modelling is a demanding test of foundation models, because it requires robust, holistic representation learning for a given data modality, rather than optimisation for a supervised prediction target alone. While recent work on…

Machine Learning · Computer Science 2026-05-12 Xiangjian Jiang , Mingxuan Liu , Nikola Simidjievski , Tassilo Klein , Mateja Jamnik

Scoring the factuality of a generated summary involves measuring the degree to which a target text contains factual information using the input document as support. Given the similarities in the problem formulation, previous work has shown…

Computation and Language · Computer Science 2022-12-01 John Glover , Federico Fancellu , Vasudevan Jagannathan , Matthew R. Gormley , Thomas Schaaf

Artificial Intelligence-generated content has become increasingly popular, yet its malicious use, particularly the deepfakes, poses a serious threat to public trust and discourse. While deepfake detection methods achieve high predictive…

Machine Learning · Computer Science 2025-07-15 Tomasz Szandala , Fatima Ezzeddine , Natalia Rusin , Silvia Giordano , Omran Ayoub

Existing benchmarks for fake news detection have significantly contributed to the advancement of models in assessing the authenticity of news content. However, these benchmarks typically focus solely on news pertaining to a single semantic…

Computation and Language · Computer Science 2024-10-16 Ziyi Zhou , Xiaoming Zhang , Litian Zhang , Jiacheng Liu , Senzhang Wang , Zheng Liu , Xi Zhang , Chaozhuo Li , Philip S. Yu

Abstractive summarization models often generate factually inconsistent content particularly when the parametric knowledge of the model conflicts with the knowledge in the input document. In this paper, we analyze the robustness of…

Computation and Language · Computer Science 2024-02-26 Jongyoon Song , Nohil Park , Bongkyu Hwang , Jaewoong Yun , Seongho Joe , Youngjune L. Gwon , Sungroh Yoon

Factuality evaluation aims to detect factual errors produced by language models (LMs) and hence guide the development of more factual models. Towards this goal, we train a factuality evaluator, FenCE, that provides LM generators with…

Computation and Language · Computer Science 2025-06-03 Yiqing Xie , Wenxuan Zhou , Pradyot Prakash , Di Jin , Yuning Mao , Quintin Fettes , Arya Talebzadeh , Sinong Wang , Han Fang , Carolyn Rose , Daniel Fried , Hejia Zhang

Large language models can generate factually inaccurate content, a problem known as hallucination. Recent works have built upon retrieved-augmented generation to improve factuality through iterative prompting but these methods are limited…

Computation and Language · Computer Science 2025-06-03 Mingda Chen , Yang Li , Karthik Padthe , Rulin Shao , Alicia Sun , Luke Zettlemoyer , Gargi Ghosh , Wen-tau Yih

The Coarse-to-Fine Few-Shot (C2FS) task is designed to train models using only coarse labels, then leverages a limited number of subclass samples to achieve fine-grained recognition capabilities. This task presents two main challenges:…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Xin-yang Zhao , Jian Jin , Yang-yang Li , Yazhou Yao

The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering by means of an additional guidance image. Where classical guided filters transfer structures using hand-designed…

Computer Vision and Pattern Recognition · Computer Science 2021-09-15 Zenglin Shi , Yunlu Chen , Efstratios Gavves , Pascal Mettes , Cees G. M. Snoek

Hallucinations pose a challenge to the application of large language models (LLMs) thereby motivating the development of metrics to evaluate factual precision. We observe that popular metrics using the Decompose-Then-Verify framework, such…

Computation and Language · Computer Science 2024-10-17 Zhengping Jiang , Jingyu Zhang , Nathaniel Weir , Seth Ebner , Miriam Wanner , Kate Sanders , Daniel Khashabi , Anqi Liu , Benjamin Van Durme

We introduce $\textbf{F}$uture $\textbf{LA}$tent $\textbf{RE}$presentation Alignment ($\textbf{FLARE}$), a novel framework that integrates predictive latent world modeling into robot policy learning. By aligning features from a diffusion…

Various studies have attempted to remove sensitive or private knowledge from a language model to prevent its unauthorized exposure. However, prior studies have overlooked the complex and interconnected nature of knowledge, where related…

Computation and Language · Computer Science 2025-10-28 Nakyeong Yang , Minsung Kim , Seunghyun Yoon , Joongbo Shin , Kyomin Jung

While Retrieval-Augmented Generation (RAG) mitigates hallucination and knowledge staleness in Large Language Models (LLMs), existing frameworks often falter on complex, multi-hop queries that require synthesizing information from disparate…

Computation and Language · Computer Science 2025-10-28 Mohammad Aghajani Asl , Majid Asgari-Bidhendi , Behrooz Minaei-Bidgoli

Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of such explanations is…

Computation and Language · Computer Science 2021-12-15 Shailza Jolly , Pepa Atanasova , Isabelle Augenstein

Finetuning provides a scalable and cost-effective means of customizing language models for specific tasks or response styles, with greater reliability than prompting or in-context learning. In contrast, the conventional wisdom is that…

Computation and Language · Computer Science 2025-03-11 Eric Zhao , Pranjal Awasthi , Nika Haghtalab

Predictive modeling often faces challenges due to limited data availability and quality, especially in domains where collected features are weakly correlated with outcomes and where additional feature collection is constrained by ethical or…

Machine Learning · Computer Science 2024-10-08 Bingxuan Li , Pengyi Shi , Amy Ward

Recourse generators provide actionable insights, often through feature-based counterfactual explanations (CFEs), to help negatively classified individuals understand how to adjust their input features to achieve a positive classification.…

Machine Learning · Computer Science 2025-06-04 Keziah Naggita , Matthew R. Walter , Avrim Blum

Generating with citations is crucial for trustworthy Large Language Models (LLMs), yet even advanced LLMs often produce mismatched or irrelevant citations. Existing methods over-optimize citation fidelity while overlooking relevance to the…

Information Retrieval · Computer Science 2026-02-24 Yixing Peng , Licheng Zhang , Shancheng Fang , Yi Liu , Peijian Gu , Quan Wang