SURE-Challenge: Evaluating Speech Evidence Before Speech-LLM Generation
Mengzhe Geng
Aug 2026
Natural Language Processing
Abstract
Speech LLMs are usually graded after they answer, although an operating system first has to decide whether a waveform should be sent to the model. We define the Speech-Unsupported Rejection Evaluation Challenge (SURE-Challenge) for this admission step. The benchmark pairs LibriSpeech-derived transcription and first-word question answering with unsupported silence, colored noise, synthetic tones, and source-ambiguous babble under disjoint source splits. Front-end ablations use Qwen2-Audio; the selected energy-plus-Whisper-score rule is then replayed before six speech/audio LLMs. On the 474-row leakage-screened SURE-Extended test set, raw Qwen2-Audio rejects 15/204 unsupported inputs, whereas the fixed rule rejects 196/204 and leaves supported accuracy unchanged. External checks delimit this number: Common Voice retention drops as the Whisper-score threshold is tightened, and no-speed babble gives 18 to 24 rejected clips out of 54 across regenerated seeds. The result identifies a pre-generation error mode missed by answer-only scoring.
NINJA (short for Needle-in-haystack jailbreak attack), a method that jailbreaks aligned LMs by appending benign, model-generated content to harmful user goals to reveal fundamental vulnerabilities in modern LMs.
R. Shah, C. Wu, Shashwat Saxena et al.· arXiv.org· 4 citations
SimulRAG, a simulator-based RAG framework with a generalized retrieval interface that translates between text and simulator parameters/outputs, is proposed, which improves informativeness and factuality over the strongest adapted RAG baselines, while UE+SBA enhances claim-level efficiency and quality.
Haozhou Xu, D. Wu, M. Chinazzi et al.· arXiv.org· 3 citations
This paper identifies two different routes through which models can acquire geometrically separable features: they can learn them from complementary co-occurrence signals in general language data, including text-number co-occurrence and cross-number interaction, or from multi-token addition problems.
Interactions are introduced as a fine-grained tool to analyze prompt sensitivity of LLMs and it is discovered that subtle changes to prompts can trigger severe instability in interactions, even when the outputs of the LLM remain the same.
Ruiyang Qin, Qingzhuo Wang, Tianhao Wang et al.· 2 citations· ⚡1
A benchmark built on the Speech Accessibility Project (SAP) dataset is introduced that tests whether diagnosis labels, clinician-derived speech ratings, and progressively richer clinical descriptions improve transcription accuracy for dysarthric speech, finding that current models do not meaningfully use this context.
P. Moure, Niclas Pokel, Bilal Bounajma et al.· arXiv.org· 2 citations
A pipeline that integrates a large language model to generate intermediate implicit premises based on the explicit premise and claim, a neuro-symbolic reasoner based on a SAT solver to determine entailment, and a neuro-symbolic reasoner based on a SAT solver to determine entailment is proposed.
Xuyao Feng, Anthony Hunter· arXiv.org· 2 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduAug 31, 2026
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
