Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation
This identifies a critical failure mode in LLM-based evaluation for QA tasks, which is incremental as it builds on existing LLM-as-a-judge methods but highlights a specific vulnerability.
The paper tackled the problem of LLM judges failing to adhere to provided references in QA evaluation when references conflict with their parametric knowledge, resulting in unreliable scores and degraded evaluation fidelity, with grading reliability dropping sharply under controlled swapped-reference conditions.
While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation tasks, little is known about their ability to adhere to a provided reference. We identify a critical failure mode of such reference-based LLM QA evaluation: when the provided reference conflicts with the judge model's parametric knowledge, the resulting scores become unreliable, substantially degrading evaluation fidelity. To study this phenomenon systematically, we introduce a controlled swapped-reference QA framework that induces reference-belief conflicts. Specifically, we replace the reference answer with an incorrect entity and construct diverse pairings of original and swapped references with correspondingly aligned candidate answers. Surprisingly, grading reliability drops sharply under swapped references across a broad set of judge models. We empirically show that this vulnerability is driven by judges' over-reliance on parametric knowledge, leading judges to disregard the given reference under conflict. Finally, we find that this failure persists under common prompt-based mitigation strategies, highlighting a fundamental limitation of LLM-as-a-judge evaluation and motivating reference-based protocols that enforce stronger adherence to the provided reference.