paper-with-me

홈 › Papers

Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation

2023-11-16 · Yifu Qiu, Varun Embar, Shay B. Cohen, Benjamin Han

Knowledge-to-text generators often struggle to faithfully generate descriptions for the input facts: they may produce hallucinations that contradict the input, or describe facts not present in the input. To reduce hallucinations, we propose a decoding-only method, TWEAK (Think While Effectively Articulating Knowledge), which can be integrated with any generator without retraining. TWEAK treats the generated sequences at each decoding step and its future sequences as hypotheses, and ranks each generation candidate based on the extent to which their hypotheses are supported by the input facts using a Hypothesis Verification Model (HVM). We first demonstrate the effectiveness of TWEAK by using a Natural Language Inference (NLI) model as the HVM and report improved faithfulness with a minimal impact on the quality. We then replace the NLI model with a task-specific HVM trained with a first-of-a-kind dataset, FATE (Fact-Aligned Textual Entailment), which pairs input facts with their original and perturbed descriptions. We test TWEAK with two generators, and the best TWEAK variants improve on average for the two models by 2.24/7.17 points in faithfulness (FactKB) in in/out-of-distribution evaluations, respectively, and with only a 0.14/0.32-point decline in quality (BERTScore).

📄 PDF Abstract BibTeX arXiv:2311.09467

Code (1)

apple/ml-tweak 공식 구현 pytorch

Tasks

Natural Language InferenceText Generation

Similar Papers 제목 키워드 기반

Think, Then Verify: A Hypothesis-Verification Multi-Agent Framework for Long Video Understanding

2026-03-05 · Zheng Wang, Haoran Chen, Haoxuan Qin, Zhipeng Wei 외 arxiv

Long video understanding is challenging due to dense visual redundancy, long-range temporal dependencies, and the tendency of chain-of-thought and retrieval-based agents to accumulate semantic drift and correlation-drive…

Video Question Answering

Hypothesis Testing Prompting Improves Deductive Reasoning in Large Language Models

2024-05-09 · Yitian Li, Jidong Tian, Hao He, Yaohui Jin

Combining different forms of prompts with pre-trained large language models has yielded remarkable results on reasoning tasks (e.g. Chain-of-Thought prompting). However, along with testing on more complex reasoning, thes…

Fact Verification

Writer-independent Feature Learning for Offline Signature Verification using Deep Convolutional Neural Networks

2016-04-04 · Luiz G. Hafemann, Robert Sabourin, Luiz S. Oliveira

Automatic Offline Handwritten Signature Verification has been researched over the last few decades from several perspectives, using insights from graphology, computer vision, signal processing, among others. In spite of …

Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework

2026-03-16 · Zhuoshang Wang, Yubing Ren, Yanan Cao, Fang Fang 외 arxiv

While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific detectors for verificat…

Self-Supervised Learning Based Handwriting Verification

2024-05-28 · Mihir Chauhan, Mohammad Abuzar Shaikh, Bina Ramamurthy, Mingchen Gao 외

We present SSL-HV: Self-Supervised Learning approaches applied to the task of Handwriting Verification. This task involves determining whether a given pair of handwritten images originate from the same or different write…

Handwriting VerificationSelf-Supervised Learning