PretrainRL: Alleviating Factuality Hallucination of Large Language Models at the Beginning (2026.findings-acl)
Copied to clipboard
Langming Liu, Kangtao Lv, Haibin Chen, Weidong Zhang, Yejing Wang, Shilei Liu, Xin Tong, Yujin Yuan, Yongwei Wang, Wenbo Su, Bo Zheng
| Challenge: | Large language models suffer from factual hallucinations where they generate verifiable falsehoods. |
| Approach: | They propose a framework that integrates reinforcement learning into the pretraining phase to consolidate factual knowledge. |
| Outcome: | The proposed framework significantly alleviates factual hallucinations and outperforms state-of-the-art methods. |
Similar Papers
Parametric Knowledge is Not All You Need: Toward Honest Large Language Models via Retrieval of Pretraining Data (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models are highly capable of answering questions, but they are often unaware of their own knowledge boundary, i.e., knowing what they know and what they don’t know. |
| Approach: | They propose a method to evaluate LLM honesty using Pythia with publicly available pretraining data. |
| Outcome: | The proposed method is based on Pythia, a truly open LLM with publicly available pretraining data. |
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation (2025.emnlp-main)
Copied to clipboard
Dingwei Chen, Ziqiang Liu, Feiteng Fang, Chak Tou Leong, Shiwen Ni, Ahmadreza Argha, Hamid Alinejad-Rokny, Min Yang, Chengming Li
| Challenge: | Existing approaches to generating factually inconsistent outputs are resource-intensive. |
| Approach: | They propose a plug-and-play intervention designed to enhance factuality by inserting premature layers formed through mathematical interpolation with adjacent layers. |
| Outcome: | The proposed intervention reduces hallucinations while outperforming baselines on four datasets. |
Pre-trained Language Models Return Distinguishable Probability Distributions to Unfaithfully Hallucinated Texts (2024.findings-emnlp)
Copied to clipboard
| Challenge: | 88-98% of cases return distinguishable generation probability and uncertainty distributions to unfaithfully hallucinated texts, regardless of their size and structure. |
| Approach: | They examine 24 pre-trained language models on 6 data sets to examine their ability to distinguish unfaithfully hallucinated texts. |
| Outcome: | The proposed training algorithm outperforms baseline models while maintaining sound general text quality measures. |
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. |
Debiasing Large Language Models with Structured Knowledge (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to reduce biases in pre-training models are hampered by their performance. |
| Approach: | They propose a method that utilizes structured knowledge to mitigate bias in LLMs . their method obviates the need for training from scratch, thus offering enhanced scalability . |
| Outcome: | The proposed method outperforms state-of-the-art (SOTA) baselines in the debiasing ability. |
Alleviating Hallucinations from Knowledge Misalignment in Large Language Models via Selective Abstention Learning (2025.acl-long)
Copied to clipboard
Lei Huang, Xiaocheng Feng, Weitao Ma, Yuchun Fan, Xiachong Feng, Yuxuan Gu, Yangfan Ye, Liang Zhao, Weihong Zhong, Baoxin Wang, Dayong Wu, Guoping Hu, Lingpeng Kong, Tong Xiao, Ting Liu, Bing Qin
| Challenge: | Large language models (LLMs) suffer from severe hallucination issues due to the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage. |
| Approach: | They propose a training objective with an abstention mechanism that selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token. |
| Outcome: | The proposed model selectively rejects tokens that misalign with the desired knowledge distribution via a special [REJ] token. |
FactCorrector: A Graph-Inspired Approach to Long-Form Factuality Correction of Large Language Models (2026.acl-long)
Copied to clipboard
Javier Carnerero-Cano, Massimiliano Pronesti, Radu Marinescu, Tigran T. Tchrakian, James Barry, Jasmina Gajcin, Yufang Hou, Alessandra Pascale, Elizabeth M. Daly
| Challenge: | Large language models (LLMs) often produce factually incorrect responses. |
| Approach: | They propose a new method that adapts across domains without retraining and leverages structured feedback to generate a correction. |
| Outcome: | The proposed method outperforms baseline methods on a VELI5 dataset and several popular long-form factuality datasets. |
KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality (2026.acl-long)
Copied to clipboard
| Challenge: | Existing Reinforcement Learning approaches rely on outcome-oriented rewards to reinforce fabricated reasoning paths when the final answer is correct. |
| Approach: | They propose a framework that integrates factual supervision directly into reasoning . they propose to decompose chain of thought into atomic facts and verify them against ground-truth knowledge . |
| Outcome: | The proposed framework reduces the Incorrect Rate on SimpleQA by 20.3% while maintaining strong performance on complex reasoning benchmarks. |
Harmful Factuality: LLMs Correcting What They Shouldn’t (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are trained for factual accuracy, but can conflict with the critical demand for source fidelity. |
| Approach: | They propose a reproducible framework to elicit and measure HFH using controlled entity-level perturbations and strategic entity selection. |
| Outcome: | The proposed framework reduces HFH rates by 50% across summarization, rephrasing, and QA tasks. |
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. |