| Challenge: | Recent studies have explored hallucinations through the lens of internal representations, proposing mechanisms to decipher LLMs’ adherence to facts. |
| Approach: | They propose to train a universal truthfulness hyperplane that distinguishes the model’s factually correct and incorrect outputs on a diverse collection of over 40 datasets and examine its cross-task, cross-domain, and in-domain generalization. |
| Outcome: | The proposed model is able to distinguish factual outputs from incorrect outputs on a diverse collection of over 40 datasets. |
Similar Papers
Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies suggest that LLMs encode internal representations of factuality when generating inaccurate or fabricated content. |
| Approach: | They propose a strategy for sampling plausible true-false factoid sentences from tabular data and a procedure for generating realistic, LLM-dependent true-False datasets from Question Answering collections. |
| Outcome: | The proposed approach lays the groundwork for future research on factuality in LLMs and offers practical guidelines for more effective evaluation. |
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) sometimes produce untruthful responses despite knowing the correct knowledge. |
| Approach: | They propose an inference-time intervention method to activate the truthfulness of Large Language Models (LLMs) by editing the features within LLM’s internal representations that govern the truthful. |
| Outcome: | The proposed method improves the truthfulness of 13 advanced LLMs by an average of 20% on TruthfulQA benchmark. |
Language Models Hallucinate, but May Excel at Fact Verification (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have produced non-factual outputs . however, current LLMs suffer from the hallucination issue . |
| Approach: | They propose to use instruction-tuned LLMs to generate factual outputs . they find that FLAN-T5-11B performs best as a fact verifier . |
| Outcome: | The proposed method outperforms more capable LLMs like GPT3.5 and ChatGPT in the human evaluation. |
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are trained on vast corpora that contain substantial knowledge but their outputs often contain confidently stated inaccuracies. |
| Approach: | They propose to encode truthfulness as a distinct linear feature, termed the "truth direction", which can classify truthfulness reliably. |
| Outcome: | The proposed model can generalize to logical transformations, question-answering tasks, in-context learning, and external knowledge sources. |
The Internal State of an LLM Knows When It’s Lying (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown exceptional performance in various tasks, but one of their main drawbacks is generating inaccurate or false information with a confident tone. |
| Approach: | They propose to train a classifier that outputs the probability that a statement is truthful based on the hidden layer activations of the LLM as it reads or generates the statement. |
| Outcome: | The proposed classifier achieves an average of 71% to 83% accuracy labeling which sentences are true versus false, depending on the LLM base model. |
On Large Language Models’ Hallucination with Regard to Known Facts (2024.naacl-long)
Copied to clipboard
Che Jiang, Biqing Qi, Xiangyu Hong, Dayuan Fu, Yang Cheng, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou
| Challenge: | Large language models are successful in answering factoid questions but are also prone to hallucination. |
| Approach: | They propose self-reporting to the model when faced with such limitations. |
| Outcome: | The proposed classifier can detect hallucinations with an 88% success rate and can be used to answer factoid questions with correct answer knowledge. |
The Curious Case of Hallucinatory (Un)answerability: Finding Truths in the Hidden States of Over-Confident Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have been shown to possess impressive capabilities, but they are not problem-free. |
| Approach: | They explore the behavior of large language models when presented with (un)answerable queries. |
| Outcome: | The proposed models encode the answerability of an input query, the authors show . they also show that the first decoded token is a strong indicator . |
The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | a growing number of researchers are studying the hallucination issue in large language models. |
| Approach: | They propose a hallucination detection benchmark and a method to detect hallucines in LLMs. |
| Outcome: | The proposed method detects hallucinations and mitigates them using different training stages. |
LLM Factoscope: Uncovering LLMs’ Factual Discernment through Measuring Inner States (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) produce outputs that deviate from factual reality, especially in sensitive applications such as medical consultation and legal advice. |
| Approach: | They propose a Siamese network-based model that leverages LLMs’ inner states for factual detection. |
| Outcome: | The proposed model achieves over 96% accuracy on a custom-collected factual detection dataset. |
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations (2026.acl-long)
Copied to clipboard
Wen Luo, Guangyue Peng, Wei Li, Shaohang Wei, Feifan Song, Liang Wang, Nan Yang, Xingxing Zhang, Jing Jin, Furu Wei, Houfeng Wang
| Challenge: | Previous work shows that large language models generate hallucinations, yet the origins and mechanisms of these signals remain unclear. |
| Approach: | They propose to validate and disentangle two different pathways for truthfulness cues . they also propose to use the same mechanism to derive self-contained evidence from the generated answer . |
| Outcome: | The proposed applications improve hallucination detection performance by integrating two different inputs. |