The paper introduces a semantic correctness taxonomy that categorizes open‑ended QA answers into eight ordered classes, distinguishing between correct, verbose, and hallucinated responses. It releases two datasets—CAP‑Correctness and CAP‑Statements—to support benchmark evaluation and NLI‑based training. The authors also propose CAP (Context‑Aware Precision), a reference‑based metric that scores question‑conditioned statements via bidirectional NLI and demonstrates superior performance under a monotonicity protocol.
By Elitsa Yotkova, Violeta Kastreva, Petar Velkov, Hristo Boyanov, Dimitar Dimitrov, Ivan Koychev, Preslav Nakov
arXiv:2610.08026v1 Announce Type: new
Abstract: In recent years, several methods for detecting when large language models (LLMs) hallucinate have been developed. These methods are often benchmarked w...
By Jorma Valjakka, Juhani Kivim\"aki, Juha Myll\"ari, Jukka K. Nurminen
arXiv:2606. 06197v1 Announce Type: cross Abstract: Question answering (QA) systems have achieved notable progress with the advent of large language models (LLMs).
By Hafez Abdelghaffar, Ahmed Alansary, Ali Hamdi
arXiv:2504. 07385v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly used for question-answering (QA), relying on static, pre-annotated references for evaluation poses significant challenges in cost, scalability, and completeness.
By Sher Badshah, Ali Emami, Hassan Sajjad
arXiv:2604. 09497v2 Announce Type: replace-cross Abstract: Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases.
By Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Emmanuel Malherbe, C\'eline Hudelot, Pierre Colombo
The paper examines how calibration rules for open‑ended question answering can be misled by the choice of correctness labels, noting that exact‑match labels can produce misleading confidence estimates. It introduces FactForm, a fact‑grounded form grader that combines reference matching with evidence retrieval, achieving lower error and higher AUROC than traditional graders on a large benchmark. FactForm’s design allows a single LLM call per answer and demonstrates stable performance across runs.
By Zhexi Feng, Bingrui Zhang, Wuxi Chen
arXiv:2608. 10315v1 Announce Type: cross Abstract: Large language models (LLMs) are powerful black-box systems, making it difficult to discern whether their answers reflect stable internal beliefs or superficial pattern matching.
By Siyang Wu, Yibo Jiang, Bryon Aragam
arXiv:2609.15561v1 Announce Type: new
Abstract: Evaluating the factual correctness of large language models (LLMs) is vital for many applications. But are our evaluation tools themselves trustworthy?...
By Sarra Gharsallah, Adele Robaldo, Mariia Tokareva, Giovanni Gatti Pinheiro, Ilyana Guendouz, Rapha\"el Troncy, Paolo Papotti, Pietro Michiardi
arXiv:2607. 22554v1 Announce Type: new Abstract: Large language models (LLMs) often achieve strong accuracy on benchmarks, yet it remains unclear how reliably they apply this knowledge when the same question is phrased in different but equivalent ways.
By Kazem Faghih, Yize Cheng, Shoumik Saha, Mobina Pournemat, Armin Gerami, Soheil Feizi
The paper introduces Evidence Sufficiency Boundary Training, a framework that teaches models to abstain from answering until the supplied evidence is fully sufficient, and to remain stable when additional redundant evidence is added. By constructing ordered evidence chains from datasets such as HotpotQA, 2WikiMultiHopQA, and MuSiQue, the method applies level supervision, a boundary flip margin, post‑boundary stability, and answer recall protection. Experiments with Qwen2.5‑3B‑Instruct and LoRA adaptation show improved boundary localization (flip accuracy 0.807 vs 0.781) and a lower unsupported‑answer rate (0.095 vs 0.101) while maintaining competitive raw QA F1.
By Haruto Sato, Yuki Tanaka, Ren Nakamura, Aoi Kobayashi, Mei Ito
arXiv:2609.24799v1 Announce Type: new
Abstract: Post-training quantization (PTQ) enables efficient deployment of large language models, and PTQ methods are usually optimized and evaluated with generi...
By Yeji Kim, Mi-Young Kim, Randy Goebel
The paper presents the first large‑scale benchmark for uncertainty quantification (UQ) calibration in long‑form scientific question answering, evaluating four UQ methods on 685,000 responses from up to 20 large language models across seven datasets. It shows that instruction tuning leads to token‑level probability polarization, undermining token‑level uncertainty signals, while reasoning model families differ in how they handle this effect. Only semantic consistency—consistency of the final answer—provides well‑calibrated outputs, demonstrating that semantic calibration remains robust in multi‑step, dependency‑rich reasoning.
By Philip M\"uller, Nicholas Popovi\v{c}, Michael F\"arber, Peter Steinbach