arXiv:2608. 06377v1 Announce Type: cross Abstract: Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong.
Language models increasingly condition their answers on external signals, and a single misleading one can turn a correct answer wrong. The obvious remedy, training models to resist such signals, hides a failure mode: a model that ignores all context looks robust yet is useless when the context is worth trusting.
JevOut demonstrates that natural, short additions to the context of decision models can flip their outputs from correct to incorrect, even when the correct answer remains unchanged. By optimizing context additions while keeping the source, question, choices, and gold answer fixed, the study found that 61.4% of initially correct decisions were redirected to a wrong option, with 45% receiving high confidence. Similar fragility was observed across three other decision systems on seven datasets, with flip rates between 64.9% and 73.2%.
arXiv:2509. 03647v2 Announce Type: replace-cross Abstract: Large language models (LLMs) increasingly serve as automated evaluators, yet they suffer from "self-preference bias": a tendency to favor their own outputs over those of other models.
arXiv:2606. 02211v1 Announce Type: cross Abstract: Large language models are often influenced by extraneous input features, such as cues revealing a user's preferred answer.
arXiv:2607. 19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet.
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.
arXiv:2606. 00334v1 Announce Type: cross Abstract: Various language domains have undergone remarkable changes in recent years; these shifts are largely attributed to the advent of Large Language Models and their misalignment with natural language usage.
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:2605. 24960v2 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) faithfulness, i.
arXiv:2608. 16515v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trust problem: retrieved context may be useful, irrelevant, or even misleading.
arXiv:2602.13576v2 Announce Type: replace-cross Abstract: Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-langu...
arXiv:2603. 03291v2 Announce Type: replace-cross Abstract: Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences.