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/chenmeiqii/teach-llm-lr

공식 코드

Improving Large Language Models in Event Relation Logical Prediction

https://github.com/chenyangh/OTTAWA

공식 코드

OTTAWA: Optimal TransporT Adaptive Word Aligner for Hallucination and Omission Translation Errors Detection

https://github.com/chiang-yuan/llamp

공식 코드

LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrieval and Distillation

https://github.com/chrisdud0257/ssl

공식 코드

SSL: A Self-similarity Loss for Improving Generative Image Super-resolution

https://github.com/chuanyang-zheng/lyra-theorem-prover

공식 코드

Lyra: Orchestrating Dual Correction in Automated Theorem Proving

https://github.com/citymind-lab/urbanvlp

공식 코드

UrbanVLP: Multi-Granularity Vision-Language Pretraining for Urban Socioeconomic Indicator Prediction

https://github.com/cityu-aim-group/sigma

공식 코드

SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection

https://github.com/cnnlstm/fslsd_hires

공식 코드

High-resolution Face Swapping via Latent Semantics Disentanglement

https://github.com/csarron/btr

공식 코드

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models

https://github.com/csguoh/refir

공식 코드

ReFIR: Grounding Large Restoration Models with Retrieval Augmentation

https://github.com/cvs-health/uqlm

공식 코드

Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers

https://github.com/d-ailin/clip-guided-decoding

공식 코드

Seeing is Believing: Mitigating Hallucination in Large Vision-Language Models via CLIP-Guided Decoding

https://github.com/d3mlab/cr-lt-kgqa

공식 코드

CR-LT-KGQA: A Knowledge Graph Question Answering Dataset Requiring Commonsense Reasoning and Long-Tail Knowledge

https://github.com/damo-nlp-sg/chain-of-knowledge

공식 코드

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources

https://github.com/damo-nlp-sg/llm-multilingual-knowledge-boundaries

공식 코드

Analyzing LLMs' Knowledge Boundary Cognition Across Languages Through the Lens of Internal Representations

https://github.com/damo-nlp-sg/vcd

공식 코드

Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

https://github.com/datadrivenwheels/scvlm

공식 코드

ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding

https://github.com/davidabrahamyan/stackrag

공식 코드

StackRAG Agent: Improving Developer Answers with Retrieval-Augmented Generation

https://github.com/dcdsf321/known_fact_hallucination

공식 코드

On Large Language Models' Hallucination with Regard to Known Facts

https://github.com/declare-lab/emma-x

공식 코드

Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning

https://github.com/declare-lab/pathfinder-prm

공식 코드

Error Typing for Smarter Rewards: Improving Process Reward Models with Error-Aware Hierarchical Supervision

https://github.com/deep-mi/yoda

공식 코드

Regression is all you need for medical image translation

https://github.com/deep-spin/ot-hallucination-detection

공식 코드

Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation

https://github.com/deepakn97/maf

공식 코드

MAF: Multi-Aspect Feedback for Improving Reasoning in Large Language Models

https://github.com/deepreasoning/neulr

공식 코드

Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond

https://github.com/deepsoftwareanalytics/llmcodinghallucination

공식 코드

LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation

https://github.com/diegogosmar/hall_evaluator

공식 코드

Hallucination Mitigation using Agentic AI Natural Language-Based Frameworks

https://github.com/diegogosmar/pinject_agentic

공식 코드

Prompt Injection Detection and Mitigation via AI Multi-Agent NLP Frameworks

https://github.com/dilab-kaist/erbench

공식 코드

ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models

https://github.com/dingchenyang99/pensieve

공식 코드

Pensieve: Retrospect-then-Compare Mitigates Visual Hallucination

https://github.com/disl-lab/finesure-acl24

공식 코드

FineSurE: Fine-grained Summarization Evaluation using LLMs

https://github.com/djning/see_beyond_seeing

공식 코드

Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentation

https://github.com/dlawjddn803/info

공식 코드

You Truly Understand What I Need: Intellectual and Friendly Dialogue Agents grounding Knowledge and Persona

https://github.com/dongguanting/dpa-rag

공식 코드

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation

https://github.com/dongyuanjushi/lightlm

공식 코드

LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation

https://github.com/dongzizhu/medvh

공식 코드

MedVH: Towards Systematic Evaluation of Hallucination for Large Vision Language Models in the Medical Context

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