Papers with Code 아카이브

Hallucination

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

1

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/lvugai/chip

공식 코드

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs

https://github.com/lycheeefish/vhexpansion

공식 코드

Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models

https://github.com/machuangtao/kg-rag4sm

공식 코드

Knowledge Graph-based Retrieval-Augmented Generation for Schema Matching

https://github.com/mahjabinnahar/fakes-of-varying-shades-survey-materials

공식 코드

Fakes of Varying Shades: How Warning Affects Human Perception and Engagement Regarding LLM Hallucinations

https://github.com/majedelhelou/BIGPrior

공식 코드

BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration

https://github.com/manestay/bordirlines

공식 코드

BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation

https://github.com/masaiahhan/correlationqa

공식 코드

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs

https://github.com/maybenotime/phd

공식 코드

A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection

https://github.com/mcgill-nlp/faithdial

공식 코드

On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?

https://github.com/mdoumbouya/codeocr

공식 코드

Handwritten Code Recognition for Pen-and-Paper CS Education

https://github.com/mdswyz/SISN-Face-Hallucination

공식 코드

Face Hallucination via Split-Attention in Split-Attention Network

https://github.com/mediatechnologycenter/absinth

공식 코드

German also Hallucinates! Inconsistency Detection in News Summaries with the Absinth Dataset

https://github.com/megagonlabs/hallucination_mds

공식 코드

From Single to Multi: How LLMs Hallucinate in Multi-Document Summarization

https://github.com/megagonlabs/llmpp

공식 코드

Step-by-step Instructions and a Simple Tabular Output Format Improve the Dependency Parsing Accuracy of LLMs

https://github.com/mengchuang123/vasparse-github

공식 코드

VASparse: Towards Efficient Visual Hallucination Mitigation for Large Vision-Language Model via Visual-Aware Sparsification

https://github.com/mhackiori/agir

공식 코드

AGIR: Automating Cyber Threat Intelligence Reporting with Natural Language Generation

https://github.com/michalislazarou/tfh_fewshot

공식 코드

Few-shot learning via tensor hallucination

https://github.com/microsoft/HaDes

공식 코드

A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation

https://github.com/microsoft/conli_hallucination

공식 코드

Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations

https://github.com/microsoft/constrainedreasoner

공식 코드

SLM Meets LLM: Balancing Latency, Interpretability and Consistency in Hallucination Detection

https://github.com/microsoft/hallucinated-references

공식 코드

Do Language Models Know When They're Hallucinating References?

https://github.com/microsoft/lmops

공식 코드

UPRISE: Universal Prompt Retrieval for Improving Zero-Shot Evaluation

https://github.com/microsoft/unilm/blob/master/Diff-Transformer/

공식 코드

Differential Transformer

https://github.com/mikegu721/gapo

공식 코드

GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization

https://github.com/mikewangwzhl/solo-performance-prompting

공식 코드

Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration

https://github.com/mitmedialab/medical_hallucination

공식 코드

Medical Hallucinations in Foundation Models and Their Impact on Healthcare

https://github.com/mitsuichen14/lrsclip

공식 코드

LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text

https://github.com/miulab/factalign

공식 코드

FactAlign: Long-form Factuality Alignment of Large Language Models

https://github.com/miulab/kg-survey

공식 코드

LLM Inference Enhanced by External Knowledge: A Survey

https://github.com/mizuumi/JDocQA

공식 코드

JDocQA: Japanese Document Question Answering Dataset for Generative Language Models

https://github.com/mk322/ever_hallu

공식 코드

Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification

https://github.com/ml-postech/selective-generation

공식 코드

Selective Generation for Controllable Language Models

https://github.com/mmiao2/Hallucination

공식 코드

Hallucination, Monofacts, and Miscalibration: An Empirical Investigation

https://github.com/modelscope/ms-swift

공식 코드

SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning

https://github.com/modelscope/swift

공식 코드

SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning

https://github.com/moranyanuka/KnowAda

공식 코드

Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.