Knowing Before Answering: Decoding Language Models for Reliable RAG

In Retrieval-Augmented Generation (RAG), retrieval may provide insufficient or conflicting information needed to answer a question. The system should not only know when to answer but also be able to identify cases in which the documents provided in RAG are insufficient or contain conflicting information. This can be framed as a three-way classification problem, where we use the model's internal signals to determine whether the provided information in the input can be classified as sufficient, insufficient, or conflicting. We create a controlled benchmark dataset that replicates a RAG setup with fictitious information and labels each instance as answerable, insufficient, or conflicting. We use hidden activations and attention-derived features as inputs to train a lightweight linear model to distinguish among the three classes. Across 16 language models spanning different architectures and a range of model sizes, our feature-based router consistently outperforms prompting-based baselines and the performance of specialised RAG-models. We further conduct analyses into the information dynamics of the models. We show that the most informative signals for the classification are available in the middle layers, with hidden activation states being more effective than attention values or the MLP-feature outputs in most of the tested models. Overall, our results suggest that language models internally encode whether retrieved evidence is sufficient to support answering, and that this signal can be decoded reliably for RAG triage.

Confidently Wrong: Detecting Hallucinations in Financial Question Answering from LLM Internal States

Large language models (LLMs) in financial applications fail most consequentially when they are confidently wrong. Hedged, uncertain answers invite scrutiny, whereas confident errors silently degrade downstream decisions without warning. We ask how reliably such confidently wrong answers, or confident hallucinations, can be detected from a model's internal activations, and whether those activations carry information beyond its observable outputs. We train linear probes on the residual stream and evaluate them on two established question-answering (QA) benchmarks built from real filings, FinQA and TAT-QA. Behavioral confidence is measured as the agreement among eight resampled answers to the same question, and probe effectiveness is compared against baselines, such as token log-probabilities and the model's own True/False self-assessment of its answer. Our findings show that among confident answers, those for which all eight resamples agree, 15-23% are wrong on FinQA. There the probes have a significant advantage over baseline methods in detecting hallucinations, holding 0.68-0.77 AUROC while the best baselines fall to 0.55-0.63, across Qwen3-8B, Llama-3.1-8B, and Gemma-2-9B. Our results suggest that probing can be a cost-effective triage mechanism for routing LLM answers to human review and quality control procedures in high-stakes financial applications.