CHAIR: Supervised hallucination detection via internal logit analysis across LLM layers
A new arXiv preprint introduces CHAIR (Classifier of Hallucination As ImproveR), a supervised framework that detects hallucinations by extracting statistical features (max, min, mean, std, slope) from token logits across all layers of an LLM. Evaluated on TruthfulQA and MMLU, CHAIR shows improved detection accuracy especially in zero-shot settings. The authors argue the approach also points toward richer internal representations for designing adaptive decoding strategies that reduce hallucinations.
Related guides (2)
Related events (8)
ClinHallu benchmark diagnoses stage-wise hallucinations in medical multimodal LLM reasoning
Researchers from Alibaba DAMO Academy introduce ClinHallu, a benchmark of 7,031 validated instances designed to identify where hallucinations originate within medical MLLM reasoning pipelines. Each instance is annotated with a structured reasoning trace decomposed into Visual Recognition, Knowledge Recall, and Reasoning Integration stages, with stage-replacement interventions to measure the causal impact of correcting each stage. The paper also demonstrates that trace-supervised fine-tuning reduces stage-wise hallucinations, offering both diagnostic and mitigation value for clinical AI systems.
LegalHalluLens: Typed hallucination auditing and calibrated multi-agent debate for legal AI
Researchers introduce LegalHalluLens, an auditing framework for hallucination in legal AI systems, evaluated across 510 contracts and 249,252 clause-level instances from the CUAD dataset. The framework introduces typed hallucination profiles across four claim categories (numeric, temporal, obligation/entitlement, factual) and a Risk Direction Index (RDI) that distinguishes omission from invention errors. A calibrated multi-agent debate pipeline reduces fabricated detections by 45% using a 4B-parameter model competitive with commercial APIs. The work reveals that aggregate hallucination rates (~52%) mask a 38-40 percentage-point gap between claim types and that two systems with identical aggregate rates can have opposite risk profiles.
BenHalluEval: Multi-Task Hallucination Evaluation Framework for Bengali LLMs
BenHalluEval introduces the first systematic hallucination benchmark for Bengali, covering four tasks (generative QA, code-mixed QA, summarization, reasoning) with 12,000 hallucinated candidates generated via GPT-5.4 across twelve hallucination types. Seven LLMs are evaluated under a dual-track protocol separating false-positive rate on ground-truth instances from hallucination detection rate on hallucinated candidates. The proposed BenHalluScore metric reveals substantial variation (7.72%–55.42%) across models and tasks, and chain-of-thought prompting is found to shift response distributions without consistently improving hallucination discrimination. The work highlights gaps in low-resource language hallucination evaluation and critiques single-track and prompting-only evaluation approaches.
The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models
Hugging Face has launched an open leaderboard specifically designed to benchmark hallucination rates across large language models. The effort aims to standardize evaluation of factual accuracy and confabulation tendencies, filling a gap in existing benchmarks that focus primarily on capability rather than reliability. The leaderboard is positioned as a community-driven, transparent resource for tracking model trustworthiness.
Why Language Models Hallucinate
OpenAI published research explaining the mechanisms behind language model hallucination. The work connects improved evaluation methods to enhanced AI reliability, honesty, and safety. The body is sparse on technical detail, but the framing positions this as foundational research relevant to alignment and deployment trust.
Sparse AutoEncoder steering reduces Whisper hallucination rate by ~5x without fine-tuning
Researchers investigate hallucination detection and mitigation in OpenAI's Whisper ASR model by probing internal encoder representations. They find that both raw activations and Sparse AutoEncoder (SAE) latents encode linearly separable hallucination signals concentrated in deeper layers. SAE-based activation steering reduces hallucination rates from 72.6% to 14.1% (Whisper small) and 86.9% to 27.3% (Whisper large-v3) on non-speech audio, with minimal WER degradation, approaching fine-tuning-level performance without weight updates.
PhantomBench: Large-scale benchmark reveals staggering hallucination rates on non-existent concepts
PhantomBench is a new benchmark comprising over 60,000 non-existent terms and entities derived from real concepts, designed to test whether language models can recognize the limits of their knowledge. Evaluating 21 models of various types and sizes, the authors find hallucination rates as high as 86.7% on average, with even frontier models failing to abstain when inputs presuppose the existence of fabricated concepts. The benchmark also serves as a proxy for studying model behavior on rare real concepts, and includes a pipeline for scalable generation of custom non-existent concept sets.
Dep-LLM: Training-free depression diagnosis framework using structured multi-factor LLM reasoning
Dep-LLM is a training-free framework for automatic depression detection from clinical interviews that uses frozen foundation LLMs without fine-tuning. The system decomposes long clinical dialogues into five thematic factors via Chain-of-Thought analysis, applies token-level entropy-based confidence modulation, and integrates multi-factor signals for final diagnosis. Evaluated on DAIC-WOZ and E-DAIC datasets, it outperforms zero-shot baselines across 21 foundation LLMs and surpasses supervised domain-specific and commercial LLMs on multiple metrics.