SOTAVerified

TruthfulQA

Papers

Showing 51–75 of 80 papers

TitleStatusHype
When Hindsight is Not 20/20: Testing Limits on Reflective Thinking in Large Language ModelsCode0
PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition DynamicsCode0
PRobELM: Plausibility Ranking Evaluation for Language Models—0
Non-Linear Inference Time Intervention: Improving LLM TruthfulnessCode1
In-Context Sharpness as Alerts: An Inner Representation Perspective for Hallucination MitigationCode2
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful SpaceCode2
SaGE: Evaluating Moral Consistency in Large Language ModelsCode0
LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loop—0
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation—0
GRATH: Gradual Self-Truthifying for Large Language Models—0
Tuning Language Models by ProxyCode2
Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without TuningCode1
Alleviating Hallucinations of Large Language Models through Induced HallucinationsCode1
Reducing LLM Hallucinations using Epistemic Neural Networks—0
Self-Evaluation Improves Selective Generation in Large Language Models—0
Uncertainty-aware Language Modeling for Selective Question Answering—0
Investigating Data Contamination in Modern Benchmarks for Large Language Models—0
On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models—0
Instruction Tuning with Human Curriculum—0
Tool-Augmented Reward ModelingCode1
RAIN: Your Language Models Can Align Themselves without FinetuningCode1
Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and EthicsCode1
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language ModelsCode2
Red-Teaming Large Language Models using Chain of Utterances for Safety-AlignmentCode1
Semantic Consistency for Assuring Reliability of Large Language Models—0
Show:102550
← PrevPage 3 of 4Next →

No leaderboard results yet.