5arXiv cs.CL (Computation and Language)·
Audit reveals protocol-level shortcuts in large audio-language model judges for speech evaluation
Researchers audit 'protocol-level shortcuts' in large audio-language models (LALMs) used as automatic judges for speech evaluation, testing across three deployment protocols: feature-blueprint judging, reference-conditioned judging, and pairwise A/B comparison. Across six judges and four attributes, several LALMs are found to rely on shortcuts rather than actual audio content — for example, incorrect specialist labels collapse emotion accuracy to 0.10 or below for five judges, and Qwen3-Omni-Thinking shows position bias in A/B comparisons. The findings indicate that high human-agreement scores can overstate judge validity, and that each model-protocol pair requires its own shortcut probe to be trustworthy.
Related guides (2)
Related events (8)
ParaPairAudioBench: Pairwise benchmark reveals large gaps in LALM paralinguistic judgment
Researchers introduce ParaPairAudioBench, a pairwise audio benchmark of 5,175 audio pairs spanning five paralinguistic dimensions (Style, Rate, Emphasis, Age, Gender) designed to evaluate Large Audio-Language Models as judges. Experiments show current LALMs lag human judgment by 32 percentage points on average and exhibit severe calibration failures, especially in ambiguous 'Tie' cases. The benchmark includes same-transcript and cross-transcript conditions to disentangle lexical from acoustic reliance, enabling more rigorous assessment of LALM reliability for speech evaluation.
BabelJudge: Benchmark for measuring LLM-as-a-judge reliability across languages and agent trajectories
BabelJudge is a new open-source benchmark and audit framework that systematically measures four failure modes in LLM-as-a-judge systems: position bias, verbosity bias, order inconsistency, and cross-lingual degradation. The framework uses a 'gold-labelling by degradation' technique to generate labeled evaluation pairs without human annotation. Evaluation of Qwen2.5-7B-Instruct-4bit across English, Hindi, Arabic, and Swahili reveals severe cross-lingual reliability drops, with Swahili order consistency collapsing to near-random (0.480). The framework is extended to agentic evaluation with nine trajectory-level perturbations and three new metrics, released as a Python package supporting 11 judge backends.
Auditing LLM-as-Judge reliability: judge upgrades are not interchangeable across model families
A new arXiv paper investigates measurement validity problems in LLM-as-judge evaluation, finding that swapping evaluator models changes scores even when candidate responses are fixed. Across four judgment datasets, the authors compare Qwen3 dense judges (1.7B–32B) and MiniMax M2/M2.7 API releases, finding that only the Qwen3 1.7B→4B upgrade yields robust adjacent gains while MiniMax adjacent releases do not. Stronger judges reduce but do not eliminate position and verbosity bias, and repeated-sample juries add little when errors are correlated. The paper argues for standardized reporting requirements including dataset slices, bias probes, error-dependence estimates, and protocol audit trails.
LLM judges over-credit incorrect answers in no-reference evaluation settings
A new arXiv paper investigates the reliability of LLM-as-judge evaluation in no-reference settings, finding that judge models systematically over-credit incorrect answers when no ground-truth is provided. Sensitivity experiments across three languages show that adding reference answers to prompts flips correct/incorrect decisions by up to 85% in some settings, with these changes aligning with human annotations. The authors propose a calibration methodology—testing judge knowledge with reference-aware samples before deploying in reference-free setups—as a blueprint for practitioners.
Acoustic cue alignment tokens improve speech emotion recognition in audio language models
Researchers study whether instruction-following audio language models (ALMs) use explicit acoustic cues in a grounded way when raw audio is already available. They derive six interpretable acoustic concept tokens from the eGeMAPS feature set and append them to text prompts, testing on FAU-Aibo and IEMOCAP benchmarks. Aligned tokens improve unweighted average recall while shuffled or corrupted tokens degrade performance, but models don't fully collapse under perturbation, indicating partial anchoring to the audio signal. The work offers a practical probing method for interpretability and robustness in affective computing with ALMs.
Benchmarking LLM judges for citation verification in deep-research systems
A new arXiv paper evaluates 8 LLM judges from 3 model families on citation quality assessment for deep-research systems, testing across 1,248 rubric decisions with human-reviewed gold labels. The study finds that cheaper models remain competitive with frontier models — GPT-5-mini achieves the strongest source-relevance F1 at 0.908 — but judges differ substantially in directional bias (pass-rate drift, false positive/negative rates) even when scalar F1 scores are similar. The key finding is that scalar F1 obscures biases that would be directly reinforced in an RL training loop, making judge calibration a prerequisite before using citation rubrics as reward signals.
Structural test oracle problem in LLM-as-judge synthetic corpora: silent failures and a validation protocol
A new arXiv paper reports a case where a shared decoding-budget parameter silently truncated hallucinated answers in a multilingual LLM-as-judge evaluation corpus, producing a spurious 32-point cross-lingual accuracy collapse that replicated robustly across sample sizes but was entirely artifactual. The authors argue this failure mode is structural to LLM-generated negative examples, which lack any mechanical item-level integrity check (the 'test oracle problem'), unlike corpora built from deterministic perturbation of gold answers. A second real bias (Markdown formatting preference) was simultaneously distorted in magnitude and sign by the same fault, illustrating that aggregate statistics cannot distinguish fabricated from distorted effects. The paper closes with a validation protocol for analysts working with oracle-less multilingual LLM-as-judge corpora.
Towards Reliable Multilingual LLMs-as-a-Judge: An Empirical Study
This paper systematically investigates strategies for extending LLM-based automatic evaluation (LLMs-as-a-Judge) to multilingual settings, covering high-, mid-, and low-resource languages (English, Spanish, Basque). The authors compare instruction translation, monolingual vs. multilingual supervision, and model size, finding that fine-tuned smaller models can match proprietary models when in-domain data is available, while zero-shot larger models are preferable out-of-domain. Two meta-evaluation datasets are extended to Spanish and Basque, and all data and code are publicly released.