paper-with-me

Papers

LargePiG: Your Large Language Model is Secretly a Pointer Generator

2024-10-15 · Zhongxiang Sun, Zihua Si, Xiaoxue Zang, Kai Zheng, Yang song, Xiao Zhang, Jun Xu

Recent research on query generation has focused on using Large Language Models (LLMs), which despite bringing state-of-the-art performance, also introduce issues with hallucinations in the generated queries. In this work, we introduce relevance hallucination and factuality hallucination as a new typology for hallucination problems brought by query generation based on LLMs. We propose an effective way to separate content from form in LLM-generated queries, which preserves the factual knowledge extracted and integrated from the inputs and compiles the syntactic structure, including function words, using the powerful linguistic capabilities of the LLM. Specifically, we introduce a model-agnostic and training-free method that turns the Large Language Model into a Pointer-Generator (LargePiG), where the pointer attention distribution leverages the LLM's inherent attention weights, and the copy probability is derived from the difference between the vocabulary distribution of the model's high layers and the last layer. To validate the effectiveness of LargePiG, we constructed two datasets for assessing the hallucination problems in query generation, covering both document and video scenarios. Empirical studies on various LLMs demonstrated the superiority of LargePiG on both datasets. Additional experiments also verified that LargePiG could reduce hallucination in large vision language models and improve the accuracy of document-based question-answering and factuality evaluation tasks.

📄 PDF Abstract BibTeX arXiv:2410.11366

Code (0)

등록된 구현이 없습니다.

Tasks

HallucinationLanguage ModelingLanguage ModellingLarge Language ModelQuestion Answering

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

From Words to Numbers: Your Large Language Model Is Secretly A Capable Regressor When Given In-Context Examples

2024-04-11 · Robert Vacareanu, Vlad-Andrei Negru, Vasile Suciu, Mihai Surdeanu

We analyze how well pre-trained large language models (e.g., Llama2, GPT-4, Claude 3, etc) can do linear and non-linear regression when given in-context examples, without any additional training or gradient updates. Our …

Language ModelingLanguage ModellingLarge Language Modelregression

Do-It-Yourself Single Camera 3D Pointer Input Device

2018-09-12 · Bernard Llanos, Yee-Hong Yang

We present a new algorithm for single camera 3D reconstruction, or 3D input for human-computer interfaces, based on precise tracking of an elongated object, such as a pen, having a pattern of colored bands. To configure …

3D Reconstruction

Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

2026-06-29 · Shihao Zhang, Yuguang Yan, Junzhe Zhang, Wei Zhao 외 arxiv

Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve realism. These signals, however, incur su…

Text-to-Video Generation

Your Dense Retriever is Secretly an Expeditious Reasoner

2025-09-27 · Yichi Zhang, Jun Bai, Zhixin Cai, Shuhan Qin 외 arxiv

Dense retrievers enhance retrieval by encoding queries and documents into continuous vectors, but they often struggle with reasoning-intensive queries. Although Large Language Models (LLMs) can reformulate queries to cap…

Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One

2024-02-19 · Tianlin Li, XiaoYu Zhang, Chao Du, Tianyu Pang 외

The widespread adoption of large language models (LLMs) underscores the urgent need to ensure their fairness. However, LLMs frequently present dominant viewpoints while ignoring alternative perspectives from minority par…

FairnessLanguage ModelingLanguage ModellingLarge Language Model