The paper introduces Evidence-Aligned Entity Verification (EAEV), a method for detecting entity-level hallucinations in retrieval-augmented generation (RAG). EAEV aligns generated entities with retrieved evidence across three dimensions and uses counterfactual stability analysis to maintain robust alignments when evidence changes. Experiments on multiple RAG benchmarks show that EAEV consistently outperforms existing hallucination detection methods and generalizes well.
By Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang
arXiv:2608.30987v1 Announce Type: cross
Abstract: Supervised fine-tuning (SFT) trains a base language model to imitate target responses, and these targets may require knowledge the base model has not...
By Arthur Becker, Jakob Kemmler, David Thulke, Christine Sch\"afer, Christian Dugast, Hermann Ney
arXiv:2607. 20515v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is critical for aligning Large Language Models (LLMs) with human preferences.
By Jingyi Huang, Ruohan Zong, Yujun Feng, Liran Ma, Lanyu Shang, Yang Zhang
arXiv:2509. 26169v2 Announce Type: replace Abstract: Alignment of large language models remains a central challenge in natural language processing.
By Fr\'ed\'eric Berdoz, Luca A. Lanzend\"orfer, Ren\'e Caky, Roger Wattenhofer
CALIBURN is a new approach to large language model (LLM) unlearning that measures a model’s confidence in undesirable knowledge and uses this measure to fine‑tune unlearning gradient updates. By doing so, it offers more precise control over what is forgotten while better preserving the model’s overall utility. Experiments on benchmarks such as MUSE and WMDP show that CALIBURN outperforms existing methods in balancing knowledge removal with utility retention.
By Zhengbang Yang, Yisheng Zhong, Junyuan Hong, Zhuangdi Zhu
The paper reproduces five factuality alignment methods for large language models—three on‑policy RL approaches (PPO, GRPO, Dr.GRPO) and two offline preference optimization methods (DPO, KTO)—using a common benchmark and evaluation metrics. None of the methods consistently outperforms the base model, and the rewards appear to favor format, length, or brevity rather than factuality or relevance. The study also highlights problems with current evaluation practices, noting that metrics and benchmarks often fail to measure prompt relevance and rely on fragile LLM judges and retrieval for verification.
arXiv:2607. 03870v1 Announce Type: new Abstract: As LLMs generate increasingly long outputs, effective uncertainty estimation must identify errors at fine-grained levels rather than discard entire responses.
By Ido Amit, Ido Galil, Ran El-Yaniv
arXiv:2609.00624v1 Announce Type: new
Abstract: A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we...
By Zeen Zhu, Zhuo Li, Weiyang Guo, Liye Zhao, Haibing Di, Yequan Wang, Jing Li
The paper introduces DEDUCE, a three‑stage framework that turns large language models into proactive error correctors by detecting input fact errors, devising correction strategies, and delivering reliable answers. It also presents MisFactQA, a dataset of factual errors, and new metrics for robustness evaluation. Experiments on TruthfulQA, FalseQA, and MisFactQA show significant gains in accuracy and error correction across Qwen, LLaMA, and Gemma models.
By Ping Wang, Xiangguo Sun, Bingbing Xu, Guocong Li, Xiaofeng Meng
A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we identify a structural mismatch in this paradigm:...
Large language models (LLMs) frequently produce confident yet factually incorrect responses when user inputs contain misleading premises, a phenomenon we attribute to fact perturbations in the input....
arXiv:2609.21227v1 Announce Type: cross
Abstract: Factual hallucination is commonly defined by incorrect factual outputs. We study a paraphrase-induced hallucination setting, where a model answers a...
By Wenhan Yu, Wenxin Wu, Hao Wang, Lei Sha