Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning

• URL: http://arxiv.org/abs/2402.15610v2
• Date: Wed, 12 Jun 2024 21:09:39 GMT
• Title: Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning
• Abstract summary: We introduce ReCoVERR, an inference-time algorithm to reduce the over-abstention of a selective vision-language system. ReCoVERR tries to find relevant clues in an image that provide additional evidence for the prediction.
• Score: 67.82016092549284
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Selective prediction minimizes incorrect predictions from vision-language models (VLMs) by allowing them to abstain from answering when uncertain. However, when deploying a vision-language system with low tolerance for inaccurate predictions, selective prediction may be over-cautious and abstain too frequently, even on many correct predictions. We introduce ReCoVERR, an inference-time algorithm to reduce the over-abstention of a selective vision-language system without increasing the error rate of the system's predictions. When the VLM makes a low-confidence prediction, instead of abstaining ReCoVERR tries to find relevant clues in the image that provide additional evidence for the prediction. ReCoVERR uses an LLM to pose related questions to the VLM, collects high-confidence evidences, and if enough evidence confirms the prediction the system makes a prediction instead of abstaining. ReCoVERR enables three VLMs (BLIP2, InstructBLIP, and LLaVA-1.5) to answer up to 20% more questions on the VQAv2 and A-OKVQA tasks without decreasing system accuracy, thus improving overall system reliability. Our code is available at https://github.com/tejas1995/ReCoVERR.

Related papers

• Answer-Level Trust Selection for Physical Vision-Language Reasoning [19.884429996574763]
  We propose Answer-Level Trust Selection (ATS) for accepting or rejecting individual VLM predictions.<n>ATS requires no fine-tuning, auxiliary verifier, or access to the model's internal logits.<n>We evaluate ATS in depth on Qwen2.5-VL-7B and across 20 VLM backbones.
  arXiv  Detail & Related papers  (2026-08-20T09:00:17Z)
• Explicit Abstention Knobs for Predictable Reliability in Video Question Answering [0.41288208387994896]
  High-stakes deployment of vision-language models requires selective prediction.<n>We investigate whether confidence-based abstention provides reliable control over error rates in video question answering.
  arXiv  Detail & Related papers  (2025-12-31T23:27:32Z)
• LEC: Linear Expectation Constraints for False-Discovery Control in Selective Prediction and Routing Systems [95.35293543918762]
  Large language models (LLMs) often generate unreliable answers, while uncertainty methods fail to fully distinguish correct from incorrect predictions.<n>We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level.<n>We propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint.
  arXiv  Detail & Related papers  (2025-12-01T11:27:09Z)
• Believing without Seeing: Quality Scores for Contextualizing Vision-Language Model Explanations [41.09442370052903]
  We propose evaluating two complementary qualities of VLM-generated explanations via two quality scoring functions.<n>We conduct a user study in which participants have to decide whether a VLM prediction is accurate without viewing its visual context.<n>We observe that showing our quality scores alongside VLM explanations improves participants' accuracy at predicting VLM correctness by 11.1%.
  arXiv  Detail & Related papers  (2025-09-30T06:34:21Z)
• To Trust or Not to Trust: On Calibration in ML-based Resource Allocation for Wireless Networks [11.718895971015339]
  This paper studies the calibration performance of an ML-based outage predictor within a single-user, multi-resource allocation framework.<n>We first establish key theoretical properties of this system's outage probability (OP) under perfect calibration.<n>We show that as the number of resources grows, the OP of a perfectly calibrated predictor approaches the expected output conditioned on it being below the classification threshold.
  arXiv  Detail & Related papers  (2025-07-23T13:23:43Z)
• ViLU: Learning Vision-Language Uncertainties for Failure Prediction [28.439422629957424]
  We introduce ViLU, a new Vision-Language Uncertainty quantification framework.<n>ViLU constructs an uncertainty-aware multi-modal representation by integrating the visual embedding, the predicted textual embedding, and an image-conditioned textual representation via cross-attention.<n>Our proposed approach is well-suited for post-hoc settings, where only vision and text embeddings are available without direct access to the model itself.
  arXiv  Detail & Related papers  (2025-07-10T10:41:13Z)
• Variational Visual Question Answering for Uncertainty-Aware Selective Prediction [17.353372524615363]
  We show the effectiveness and competitive edge of variational Bayes for selective prediction in Visual Question Answering (VQA) for the first time.<n>This method improves calibration and yields significant gains for selective prediction on VQA and Visual Reasoning.<n>In addition, we propose a new risk-averse selector that outperforms standard sample averaging by considering the variance of predictions.
  arXiv  Detail & Related papers  (2025-05-14T17:40:22Z)
• From Trial to Triumph: Advancing Long Video Understanding via Visual Context Sample Scaling and Self-reward Alignment [51.3011761744484]
  Multi-modal Large language models can only process a finite number of frames in a single inference. We propose multiple predictions through visual context sampling, followed by a scoring mechanism to select the final prediction. Experiments show that this approach covers the correct answer for a high percentage of long video questions.
  arXiv  Detail & Related papers  (2025-03-26T11:53:03Z)
• Correct after Answer: Enhancing Multi-Span Question Answering with Post-Processing Method [11.794628063040108]
  Multi-Span Question Answering (MSQA) requires models to extract one or multiple answer spans from a given context to answer a question. We propose Answering-Classifying-Correcting (ACC) framework, which employs a post-processing strategy to handle incorrect predictions.
  arXiv  Detail & Related papers  (2024-10-22T08:04:32Z)
• Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors [29.892041865029803]
  Conversation forecasting tasks a model with predicting the outcome of an unfolding conversation. It can be applied in social media moderation to predict harmful user behaviors before they occur. This paper explores what extent model uncertainty can be used as a tool to mitigate potential biases.
  arXiv  Detail & Related papers  (2024-10-17T15:07:53Z)
• Calibrated Large Language Models for Binary Question Answering [49.1574468325115]
  A well-calibrated model should produce probabilities that accurately reflect the likelihood of its predictions being correct. We propose a novel approach that utilizes the inductive Venn--Abers predictor (IVAP) to calibrate the probabilities associated with the output tokens corresponding to the binary labels.
  arXiv  Detail & Related papers  (2024-07-01T09:31:03Z)
• Conformal Language Modeling [61.94417935386489]
  We propose a novel approach to conformal prediction for generative language models (LMs) Standard conformal prediction produces prediction sets with rigorous, statistical guarantees. We demonstrate the promise of our approach on multiple tasks in open-domain question answering, text summarization, and radiology report generation.
  arXiv  Detail & Related papers  (2023-06-16T21:55:08Z)
• Conformal Prediction Regions for Time Series using Linear Complementarity Programming [25.094249285804224]
  We propose an optimization-based method for reducing conservatism to enable long horizon planning and verification. We show that this problem can be cast as a mixed integer linear complementarity program (MILCP), which we then relax into a linear complementarity program (LCP)
  arXiv  Detail & Related papers  (2023-04-03T15:32:38Z)
• Uncertainty Quantification with Pre-trained Language Models: A Large-Scale Empirical Analysis [120.9545643534454]
  It is crucial for the pipeline to minimize the calibration error, especially in safety-critical applications. There are various considerations behind the pipeline: (1) the choice and (2) the size of PLM, (3) the choice of uncertainty quantifier, (4) the choice of fine-tuning loss, and many more. In response, we recommend the following: (1) use ELECTRA for PLM encoding, (2) use larger PLMs if possible, (3) use Temp Scaling as the uncertainty quantifier, and (4) use Focal Loss for fine-tuning.
  arXiv  Detail & Related papers  (2022-10-10T14:16:01Z)
• Learning to Predict Trustworthiness with Steep Slope Loss [69.40817968905495]
  We study the problem of predicting trustworthiness on real-world large-scale datasets. We observe that the trustworthiness predictors trained with prior-art loss functions are prone to view both correct predictions and incorrect predictions to be trustworthy. We propose a novel steep slope loss to separate the features w.r.t. correct predictions from the ones w.r.t. incorrect predictions by two slide-like curves that oppose each other.
  arXiv  Detail & Related papers  (2021-09-30T19:19:09Z)
• Aligned Contrastive Predictive Coding [10.521845940927163]
  We investigate the possibility of forcing a self-supervised model trained using a contrastive predictive loss to extract slowly varying latent representations. Rather than producing individual predictions for each of the future representations, the model emits a sequence of predictions shorter than that of the upcoming representations to which they will be aligned.
  arXiv  Detail & Related papers  (2021-04-24T13:07:22Z)
• Controlled abstention neural networks for identifying skillful predictions for regression problems [0.0]
  We introduce a novel loss function, termed "abstention loss", that allows neural networks to identify forecasts of opportunity for regression problems. The abstention loss is applied during training to preferentially learn from the more confident samples.
  arXiv  Detail & Related papers  (2021-04-16T17:16:32Z)
• AutoCP: Automated Pipelines for Accurate Prediction Intervals [84.16181066107984]
  This paper proposes an AutoML framework called Automatic Machine Learning for Conformal Prediction (AutoCP) Unlike the familiar AutoML frameworks that attempt to select the best prediction model, AutoCP constructs prediction intervals that achieve the user-specified target coverage rate. We tested AutoCP on a variety of datasets and found that it significantly outperforms benchmark algorithms.
  arXiv  Detail & Related papers  (2020-06-24T23:13:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.