Knowing Is Not Enough: Information Retrievability as a Precondition to Effective LLM Oversight

Large language models (LLMs) are increasingly embedded in organizational work, yet their errors often pass human review. Prior research locates such failures in users' capability to review LLM output or their engagement in doing so. We develop an alternative, retrieval-based account of human oversight and posit that error detection is more effective when oversight-relevant information is accessible to users at the moment of review. Across two randomized lab-in-the-field experiments with 640 customer-facing employees, we show that self-generated explanations improve error detection and strengthen recall of verification-relevant reasoning, while cues that reactivate such reasoning help sustain detection under repeated LLM use. Theoretically, we identify information retrievability as a distinct precondition for effective oversight and specify generative encoding and cue-supported reactivation as mechanisms that build and sustain it. Practically, lightweight onboarding self-explanations and daily retrieval cues can make human oversight more resilient as LLM use becomes routine.

RPCBench: A Benchmark for Proactive Premise Critique in LLM-based Recommendation

Large language models are increasingly used as interactive recommender assistants. Their evaluation should therefore go beyond plausible item recommendation and test whether they can recognize flawed recommendation requests. Existing recommender benchmarks mainly assess ranking, generation, or preference satisfaction, while existing error-detection benchmarks are usually not grounded in recommendation-specific user and candidate evidence. To address this gap, we introduce RPCBench, a benchmark for evaluating Recommender-Premise Critique: the ability to detect, diagnose, and properly handle faulty premises in natural-language recommendation requests. RPCBench contains evidence-grounded test instances from five recommendation domains and covers ten types of premise failures. Each instance provides a visible recommendation context and a corrupted user query. We further design a fine-grained evaluation framework that measures proactive detection, error localization, post-detection handling strategy, and evidence faithfulness. Through a systematic evaluation of 11 LLMs, we find that proactive detection is the main bottleneck in Recommender-Premise Critique, and models perform worst on underspecified-premise errors. We also observe that target-critical information density matters more than redundant evidence, and that longer reasoning does not monotonically improve critique quality: performance peaks at intermediate reasoning length, while overly long reasoning is accompanied by an overthinking penalty. The code is available at https://github.com/ZhongruChen/RPCBench.

Error Detection for PET/CT Radiology Reports: Domain-Specific vs Large Language Models

Errors in radiology reports can adversely affect patient treatment, yet automated report quality assurance remains challenging because errors are often subtle and require domain expertise to detect. Although large language models (LLMs) have recently been proposed for radiology report verification, their ability to detect clinically meaningful errors beyond chest X-ray datasets remains under-explored. To this end, we present the first systematic evaluation of language models for PET/CT report error detection, comparing compact domain-specific models with SOTA open-weight LLMs. We collected 30,633 oncology FDG PET/CT reports from 23 radiologists over 10 years. We trained domain-specific BERT models to detect clinically motivated synthetic reporting errors and evaluated alongside zero-/few-shot Qwen3-32B, Gemma-3-27B and Llama-3.3-70B on a held-out benchmark of 11,500 reports. A 15M-parameter model achieved 94.4% balanced accuracy with a 5.8% false-positive rate, compared with 84.0% for the strongest prompted LLM. Task-specific adaptation of Llama-3.3-70B closed this performance gap (94.4%) but retained substantially greater computational requirements. Our results suggest that domain-specific training matters more than model scale for PET/CT report error detection, supporting compact models as an accurate and computationally efficient approach to automated radiology report quality assurance.

MMPCBench: Benchmarking Multimodal Large Language Models on Proactive Critique of Flawed Inputs

As Multimodal Large Language Models (MLLMs) evolve into sophisticated interactive assistants, their reliability depends not only on following instructions but also on validating them. We define Proactive Critique as the model's autonomous ability to identify, analyze and fix faulty user inputs without extra prompts. However, evaluations mainly test models under ideal circumstances or simple refusal behaviors, largely ignoring active error processing. To fill this gap, we propose MMPCBench, a comprehensive framework for evaluating MLLMs' proactive critique competence. It features a fine-grained taxonomy of 4 primary error types spanning 12 subcategories, ranging from cross-modal contradictions to missing visual premises. We adopt a hierarchical evaluation protocol to measure models' error detection, diagnosis and resolution performance, and apply alignment-aware metrics to assess the coherence between internal reasoning and final responses. Tests on 14 mainstream MLLMs show obvious weaknesses in proactive critique, especially in dealing with subtle visual anomalies. Notably, we identify a pervasive "consistency gap": reasoning models can often correctly identify and analyze errors during internal reasoning yet suppress these valid insights in final outputs to prioritize response compliance. The code and data is available at https://github.com/ALIENS32/MMPCBench.

The Calls are Coming from Inside the Model: Investigating Probe-based Detection of Tool-Calling Errors in LLMs

The hidden states of large language models (LLMs) are known to capture rich information relating to model knowledge and behavior that can be hard to extract from examination of input and output alone. As LLM-based systems increasingly interface with the external world, one area of concern is detecting incorrect or improper use of tools. Motivated by this, we study the effectiveness of using linear probes to detect incorrect tool-calls, measuring probe efficacy across 18 tool-calling LLMs evaluated on the Berkeley Function Calling Leaderboard. Overall, we find that probing is an effective means to catch a range of different tool-calling errors, including errors arising from using an argument that has the wrong value but the correct type, which might not be recorded by standard logging frameworks. Important factors in success include model size, probing layer, and model post-training type. We also show that probes are capable of generalizing to novel types of errors, which is critical in real world deployments.

Toward Better Assessment of LLMs' Performance in Clinical Error Detection

Automated detection of errors in clinical documentation is a promising application of large language models (LLMs), yet decisions to deploy such models rest on benchmarks that evaluate each clinical note in isolation. Error-detection benchmarks are typically constructed by injecting errors into notes, such that each erroneous note has a natural counterpart. Aggregate discriminative metrics (e.g., balanced accuracy or F1) do not exploit this structure. We show that this omission is consequential. In particular, evaluating 15 diverse LLMs on 4 standardized clinical error-detection test sets across 3 languages, we find that 13 of 15 models fall below the level of random pairwise discrimination, even while achieving F1 scores that standard practice would read as moderate. We also observe that the underlying bias patterns differ across languages: the same model can default to "no error" on one language and over-flag errors on another. To diagnose where discrimination breaks down, we further introduce a procedure to score the evidence models cite in their outputs. We find that while models consistently locate error-relevant content, they fail to produce the corresponding correct verdict on the clean counterpart. Finally, we show that F1 and pairwise accuracy are driven in opposite directions by the same underlying bias, so that ranking models by F1 may systematically promote the weakest discriminators. For safety-critical clinical NLP applications, we advocate for supplementing aggregate metrics with paired evaluations in benchmark reporting. Code and analysis scripts are available at https://github.com/healthylaife/paired-clinical-eval.

TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories

LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Critical error detection aims to locate the earliest error step in a failed trajectory that is responsible for the final failure. However, progress faces two main challenges. First, long trajectories make it difficult to identify individual errors, since the evidence for judging a step may be scattered across distant instructions, observations, and prior context. Second, failed trajectories often contain multiple local errors with different downstream effects, only some of which remain responsible for the final failure. In this work, we propose TrajDebug, an error-lifecycle tracing framework that addresses long-trajectory error discovery with multi-granularity history compression and evidence-based error identification, and supports critical attribution by tracing each error's resolution status and terminal impact. We further construct TrajErrBench, a benchmark of 486 manually annotated failed trajectories from Tau2Bench and SWE-Bench Pro, covering realistic tool-use and coding scenarios. Experiments across diverse agent benchmarks show that TrajDebug achieves the best overall performance over existing baselines, and application studies further demonstrate that its diagnoses provide actionable feedback for improving downstream agent success. We will release the codes and data to facilitate further research.

The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought Dynamics

Chain-of-thought (CoT) reasoning improves large language model (LLM) performance while also providing an observable interface to the model's reasoning process. Existing approaches that leverage verbalized CoTs to monitor reasoning correctness, however, largely evaluate the semantic correctness or consistency of individual intermediate steps, rather than how the reasoning process evolves across the trace. As a result, failures distributed across the reasoning trajectory, rather than those localized to a single incorrect step, remain comparatively underexplored. Furthermore, verbalized CoTs need not faithfully reflect the model's internal reasoning, motivating analyses that do not treat individual statements as literal accounts of internal computation. In this work, we therefore ask whether the dynamics of visible CoT can be leveraged to systematically distinguish successful from failed reasoning without assuming such semantic faithfulness. We study a range of LLMs on verifiable Boolean satisfiability tasks with variable complexity, enabling controlled comparisons near each model's capability frontier. Tagging CoT sentences by reasoning function reveals premature verification collapse on SAT problems: incorrect traces enter clause checking earlier, repeat similar operations, and finalize sooner. On UNSAT problems, models presumptuously move towards incorrect SAT conclusions, checking candidate assignments rather than deriving contradictions across constructed cases. Subsequently, a targeted proof-search prompt intervention raises Llama3-70B accuracy from 13.3% to 85%, correcting 84.6% of these errors. These results show that capability failures can manifest as distributed, task-dependent changes in the structure of visible reasoning, and that CoT dynamics agnostic to whether the verbalized trace reflects the model's internal computations can help diagnose and correct failures.

Do large language models scrutinise what they review? A multimodal audit of scoring calibration, error detection, and author-identity effects

Large language models (LLMs) are increasingly used to generate peer reviews, prompting examination of their capacity for critical evaluation. This study evaluates two multimodal LLMs, Qwen2.5-VL-72B and Pixtral-Large-124B, as reviewers across 165 submissions to the 2026 International Conference on Learning Representations, a venue that postdates both models' training cutoffs. Manuscripts were presented to both models with author identities blinded, replaced with high-prestige affiliations, or replaced with low-prestige affiliations, and in either text-only or text-with-figure format. Additionally, 145 verifiably detectable errors were inserted into 55 manuscripts to assess error identification under natural and verification-oriented prompts. Across all manuscript groups, including rejected submissions, LLM scores ranged from 7.0 to 8.1, whereas human mean scores ranged from 3.4 to 6.8. The models detected 12.1\% of the verified errors under natural prompting, and a one-sentence verification instruction increased detection to 22.2\%; however, 78\% of the errors remained undetected. Providing figures reduced error detection while increasing review scores. No visual error was reliably verified against its corresponding figure, and half of the text-only reviews described figures that were not provided. Author identity did not influence either review scores or error detection. LLM editorial decisions exactly matched those produced by simple score averaging.

Small Vision-Language Models Know When They Are Wrong But Cannot Say So: A Two-Model Study of Stated versus Internal Confidence Under Realistic Image Degradation

Vision-language models (VLMs) are increasingly deployed on consumer hardware where input images are degraded by compression, camera shake, and poor lighting. In such settings, a reliable uncertainty signal matters more than raw accuracy, because it determines when a system should defer rather than answer. We evaluate two small open-weight VLMs -- Qwen2-VL-2B-Instruct and SmolVLM-Instruct -- across six realistic photographic degradations at three severity levels, comparing two confidence signals: the confidence the model states in natural language, and the model's own mean token probability over its generated answer. Across 3,800 predictions, we find a large and consistent gap. Verbalized confidence in Qwen2-VL is almost constant (mean 0.87-0.90 across all conditions) and detects its own errors at chance level (AUROC 0.39-0.75, typically ~0.50), while internal token probability from the same model separates correct from incorrect answers with AUROC 0.92-0.99. In SmolVLM, verbalized confidence proved largely unobtainable: across three prompt templates, only one of five pilot attempts produced a parseable confidence value, while internal probability again yielded above-chance error detection (AUROC 0.54-0.92). Both models fail in the same place: under severe underexposure, accuracy collapses (0.99->0.22 for Qwen2-VL, 0.97->0.42 for SmolVLM) while both confidence signals barely move, and internal error-detection falls to chance. We conclude that small VLMs encode usable self-knowledge that their verbalized output does not express, that internal probability is therefore the better deferral signal in constrained deployment, and that neither signal should be trusted under severe low-light conditions.

CURED: Creating, Understanding, and Repairing Errors Demonstrator

Detecting and cleaning errors in tabular data is a prerequisite for data intense software applications. Recent research at the intersection of Machine Learning (ML) and Database Management Systems (DBMS) highlights the potential of statistical learning algorithms for error detection and cleaning. This paper combines our recent work on ML-based data cleaning and error models in a unified demonstrator. The web application allows users to upload tabular data, perturb the data with realistic data dependent errors and use modern ML methods to clean and understand error mechanisms in data. Our demonstrator helps to bridge the gap between theoretical advancements and intuitive practical insights in the context of error models and data cleaning algorithms for tabular data. The demonstrator is available at https://cured.demo.calgo-lab.de/

GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video

While multimodal Large Language Models (MLLMs) excel at offline video understanding, an interesting question of how far they are from serving as a real-time procedural coach remains unknown. Such a role typically requires an MLLM to continuously monitor the execution, detect mistakes, and provide corrective guidance in a closed-loop interaction. In this paper, we construct GuideMe, the first multi-domain benchmark for streaming video that supports training and evaluation of MLLMs for closed-loop interactive task guidance. It comprises 2,458 videos spanning 223.7 hours across diverse domains (\eg, cooking, object manipulation, daily-life guidance, and fitness), with 47,775 interaction samples covering next-step instructions, completion feedback, error detection, and corrective guidance. To evaluate existing models on GuideMe, we design a three-component assessment framework to measure the capabilities of representative MLLMs, which consists of temporal-semantic bipartite matching for sequence-level alignment, behavioral classification for intervention timing, and LLM-as-a-Judge for content quality. Extensive experiments highlight a critical performance asymmetry: despite excelling at providing instructions, existing MLLMs consistently fail to identify execution errors and respond with corrective feedback. Code and data are released at https://fawnliu.github.io/project/guideme.

When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

While large language models (LLMs) perform well on table tasks, they still make data referencing errors (DREs), i.e., incorrectly citing or omitting table values, despite understanding the table structure. Beyond final-answer accuracy, DREs directly compromise the correctness and reliability of intermediate reasoning steps. Yet prior studies have only offered limited, small-scale analyses. In this work, we present the first systematic evaluation of tabular data referencing errors across different models and tasks. Our results show that DREs occur across all tested models (1.7B to 20B parameters). Furthermore, we demonstrate that incorporating data referencing as a critic significantly improves answer accuracy up to 12.0%, through critic-based filtering and rejection sampling. Finally, we trained a lightweight 4B-parameter critic model that achieves an average F1 score of 78.2% in detecting both in-distribution and out-of-distribution DREs, and effectively assists inference for larger models.

ESTANet: Efficient Online Error Detection in Procedural Videos via Prediction Inconsistency

An efficient and accurate system for detecting errors in procedural tasks is crucial for supporting human needs in daily life, as it can provide instant notifications and guide people to correct mistakes. In this work, we study real-time online error detection in procedural videos from a simple but overlooked perspective: the prediction behavior of action detectors themselves. Instead of designing complex architectures or specialized supervision, we observe that action detectors naturally exhibit different prediction characteristics depending on their sensitivity to input dynamics and temporal context. We therefore propose ESTANet (Error-Sensitive and Temporally-vArying Network), a lightweight framework that detects errors by exploiting inconsistencies among action predictions produced by a small set of action detectors. We construct standard and error-sensitive action detectors that behave similarly on correct executions but respond differently when errors occur. Meanwhile, detectors operating with different temporal contexts further amplify prediction inconsistencies when the procedure deviates from the intended sequence. During inference, we detect errors by aggregating mismatches between standard and error-sensitive predictions through majority voting to flag frames that contain errors. Extensive experiments on EgoPER, Assembly-101-O, and EPIC-Tent-O demonstrate that ESTANet achieves state-of-the-art performance in online error detection while maintaining real-time efficiency with a lightweight architecture. Our results highlight that leveraging the intrinsic properties of action detectors can yield a powerful and practical solution for online error detection without increasing architectural design complexity.

Speaking in Self-Assessing Tongues: On the Verbalized Confidence of LLMs in Machine Translation

The rapid rise in popularity of large language models (LLMs) for translation calls for a thorough study of the reliability of their confidence in their own outputs. Unlike many generation tasks, translation errors and confidence levels can be useful at different levels of granularity (tokens, words, or spans). Unsupervised approaches based on internal signals like predicted probabilities can be misleading because they reflect certainty among alternatives rather than correctness. In addition, they require access to such internal signals. Here, we devise five verbalized methods of extracting an LLM's per-token confidence without those shortcomings and compare their reliability with that of the model's internal signals of certainty. We evaluate reliability using two forms of alignment: fine-grained error detection and calibration. For both, internal and verbalized methods perform similarly, although results vary by model. Interestingly, we find little to no correlation between internal and verbalized methods.

ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset

Multi-modal data management has emerged as a central research topic in the database community, spanning data integration, semantic query processing, and data quality assessment. Despite this growing interest, the community lacks large-scale, real-world datasets combining tables, text, and images. We present ArtiFact, a multi-modal cultural heritage dataset of 651045 museum records collected from the Metropolitan Museum of Art, the Art Institute of Chicago, and the Rijksmuseum. We demonstrate the utility of ArtiFact through two downstream tasks. For cross-modal error detection, we introduce a curated taxonomy of seven error categories injected into 130209 records and show that reliably detecting subtle domain-specific errors such as material anachronisms and temporal shifts remain an open challenge. For semantic query processing, we show that current systems struggle with queries involving cultural proximity, ambiguous object types, and historically contingent terminology. Our results position ArtiFact as a challenging benchmark for multi-modal data management research.

The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models

Recent works show that LLM agents struggle to correct errors in their own reasoning traces, despite their ability to correct errors from external sources. We ask whether this reflects a capability deficit or an artifact of the role labeling. To test this, we design a training-free intervention, source-conditioned role relabeling, that keeps the erroneous claim byte-identical and varies only its message role. The claim is presented inside the agent's "<thought>", a user message, a tool response, or a system "<memory>" block. We test 12 model-domain combinations spanning closed-weight APIs and open-weight models from 70B-class down to smaller families. Relabeling "<thought>" to an external role increases the explicit-correction rate by 23 to 93 percentage points, significant in 10 of 12 experimental settings. This suggests that these models' failure to detect a self-generated error is largely an artifact of how the claim is role-labeled in the chat template, rather than a pure cognitive deficit. The most effective role label is domain-dependent: "<memory>" dominates in most math experiments, while a user message dominates in logical deduction. Recognizing role-label handling as a key experimental variable in instruction tuning presents a more direct path to closing the self-correction gap.d

Hardware-aware Low-latency Quantum Compilation with Data-driven Lightweight Error Detection for Early Fault-Tolerant Systems

Noisy intermediate-scale quantum (NISQ) processors are entering an early fault-tolerance regime where full quantum error correction carries prohibitive resource costs, yet lightweight error detection can meaningfully improve algorithmic success rates. Existing compilation and error-detection toolchains treat these concerns in isolation, with no principled way to balance detection overhead against success probability under latency constraints. We present an integrated hardware-aware compilation and data-driven quantum error-detection (QED) framework that jointly optimises qubit mapping, SWAP insertion, and syndrome-schedule placement via a noise-weighted cost function and a learned multi-objective scheduler. Simulation experiments on an HPC cluster using GPU-accelerated density-matrix simulation (NVIDIA cuQuantum SDK) across VQE, phase-estimation, and Grover benchmarks, three noise profiles, and circuit sizes of 6-20 qubits (depths 10-160), show that joint co-design raises algorithmic success probability by up to 68 percent (95 percent CI: 60 percent to 76 percent) over SABRE on an 8-qubit VQE instance with post-selection.

Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents

Ensuring the accuracy of financial documents is critical for economic analysis, regulatory compliance, and corporate decision-making. Several studies have shown that Large Language Models (LLMs) perform well in many financial tasks, such as stock price movements and financial analytics. However, a critical task remains unexplored: the ability of LLMs to identify errors in financial documents. In this paper, we introduce \textbf{FinED-Bench}, the first publicly \textbf{Bench}mark for \textbf{Fin}ancial \textbf{E}rror \textbf{D}etection across three levels of cognitive complexity. FinED-Bench covers nine real-world financial scenarios, and includes over 900 documents reported in 2025 that are unseen by existing language models. We detail the benchmark construction process and evaluate several advanced LLMs (e.g., GPT-4o, Qwen3-14B) on this tasks, which requires both financial domain knowledge and reasoning capabilities. Experimental results show that current LLMs still struggle with this task, especially in high-complexity cases. Besides, supervised fine-tuning can significantly improve the performance of weaker LLMs on this task. Our data and code are available at https://github.com/hedyHe/FinED-Bench.

Towards Characterizing Scientific Image Utility and Upgradability

Scientific images function as critical evidence in research communication, yet their integrity faces unprecedented threats from AI-generated content that introduces subtle but consequential errors. Existing evaluation paradigms prove inadequate: perceptual quality metrics poorly correlate with scientific validity, while language models lack domain-specific verification capabilities. To address this gap, we propose the \textbf{S}cientific \textbf{I}mage \textbf{U}tility and \textbf{U}pgradability \textbf{A}ssessment (\textbf{SIU$^2$A}) framework, which introduces two complementary dimensions for scientific image evaluation. \textbf{Utility} encompasses \textit{error detection} (identifying scientific inaccuracies) and \textit{correction feasibility} (assessing whether errors can be reliably repaired). \textbf{Upgradability} measures the quality of correction. We categorize scientific image corruption into four fundamental types: Detail Distortion, Incompleteness, False Content, and Entity Confusion. Based on this taxonomy, we construct SIU$^2$A-Benchmark, a dataset with expert annotations for error identification and repair. The framework implements a two-stage evaluation protocol: the \textit{Utility} stage evaluates error detection capability and repair instruction generation, while the \textit{Upgradability} stage assesses whether corrections faithfully restore scientific validity without compromising existing accurate information. Experiments reveal that current multimodal systems exhibit significant limitations in both scientific error assessment and faithful correction, exposing a fundamental gap between visual perception and scientific usability.

When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning

When does multi-agent debate help data cleaning, and when does it hurt? Across three benchmarks, four model families, and over 6,000 task-condition pairs, we find debate's effect reverses sign: it degrades generation across all four models (-1.6 to -15.5pp) through critique-induced confusion (CIC), hallucinated Critic feedback that the Generator accepts uncritically, yet improves error detection (+27.4pp F1, d=1.0). We derive a debate benefit condition: debate helps when the probability of rescuing a wrong output (Critic verification odds weighted by fixability) exceeds the probability of destroying a correct one. A factorial experiment proves adversarial separation is essential: self-verification with identical tools fails, while a separate Critic with code-execution grounding and evidence-gated generation produces the first debate configuration to significantly exceed single-agent on a generative task (+5.3pp, p<0.05). The condition correctly predicts all nine task types and generalizes with zero false positives across 19 published comparisons in seven domains.