Papers with Code 아카이브
TruthfulQA
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/Avmb/adversarial_MT_prompt_injection
공식 코드A test suite of prompt injection attacks for LLM-based machine translation
https://github.com/RLHFlow/RLHF-Reward-Modeling
공식 코드https://github.com/SafeAILab/RAIN
공식 코드RAIN: Your Language Models Can Align Themselves without Finetuning
https://github.com/adkipnis/metabench
공식 코드$\texttt{metabench}$ -- A Sparse Benchmark to Measure General Ability in Large Language Models
https://github.com/alisawuffles/proxy-tuning
공식 코드https://github.com/asacooperstickland/kl-then-steer
공식 코드Steering Without Side Effects: Improving Post-Deployment Control of Language Models
https://github.com/declare-lab/red-instruct
공식 코드Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment
https://github.com/eggachecat/chair
공식 코드https://github.com/ernie-research/Tool-Augmented-Reward-Model
공식 코드https://github.com/esteng/pragmatic_calibration
공식 코드LACIE: Listener-Aware Finetuning for Confidence Calibration in Large Language Models
https://github.com/githubhyz/delta
공식 코드https://github.com/harshraj172/measuring-reliability-of-llms
공식 코드Measuring Reliability of Large Language Models through Semantic Consistency
https://github.com/hillzhang1999/icd
공식 코드Alleviating Hallucinations of Large Language Models through Induced Hallucinations
https://github.com/hitum-dev/pollmgraph
공식 코드PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics
https://github.com/hitz-zentroa/truthfulqa-multi
공식 코드Truth Knows No Language: Evaluating Truthfulness Beyond English
https://github.com/hiyouga/llama-factory
공식 코드Alleviating Hallucinations of Large Language Models through Induced Hallucinations
https://github.com/hkust-nlp/activation_decoding
공식 코드In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination Mitigation
https://github.com/ictnlp/truthx
공식 코드TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
https://github.com/imoneoi/openchat
공식 코드https://github.com/jongjyh/trfr
공식 코드https://github.com/launchnlp/actcab
공식 코드Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding
https://github.com/likenneth/honest_llama
공식 코드Inference-Time Intervention: Eliciting Truthful Answers from a Language Model
https://github.com/mohamedhisham20/truthfulqa_phi
공식 코드https://github.com/qbetterk/VarBench
공식 코드VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation
https://github.com/rlhflow/online-rlhf
공식 코드https://github.com/samsung/nl-iti
공식 코드Non-Linear Inference Time Intervention: Improving LLM Truthfulness
https://github.com/sftekin/rl-focal
공식 코드Multi-Agent Reinforcement Learning with Focal Diversity Optimization
https://github.com/shreya1313/llm-unlearning
공식 코드https://github.com/sylinrl/truthfulqa
공식 코드https://github.com/ucsc-vlaa/sight-beyond-text
공식 코드Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics
https://github.com/vnnm404/SaGE
공식 코드https://github.com/voidism/dola
공식 코드DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
https://github.com/yanhong-lbh/llm-selfreflection-eval
공식 코드When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language Models
https://github.com/yicheng98/integrativedecoding
공식 코드Integrative Decoding: Improve Factuality via Implicit Self-consistency
https://github.com/zhengxiangshi/instructionmodelling
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.