This has been addressed in7 prior work [4, 3] by finetuning VLMs on a given corpus for a given task [5] and8 conducting zero-shot evaluations on a new corpus [7]. However, the mere use of an9 unseen corpus for evaluation does not imply it is OOD. Q1 What do the instances that comprise the dataset represent (e.g., documents, photos,24 people,countries)? Pleaseprovideadescription.26 (a) We provide 384k image-text pairs. Q3 Does the dataset contain all possible instances or is it a sample (not necessarily ran-36 dom) of instances from a larger set? If the dataset is a sample, then what is the larger37 set?

Finally, generate a new brief description mainly based on the originalnull description with attributes information incorporated. Thenull narratives should be similar to the original description.null

Contrastive vision-language models continue to be the dominant approach for image and text retrieval. Contrastive Language-Image Pre-training (CLIP) trains two neural networks in contrastive manner to align their image and text embeddings in a shared latent space. Recent results evaluating CLIP on negated or paraphrased text have shown mixed performance because negation changes meaning radically with minimal lexical changes, while paraphrasing can create very different textual expressions with the same intended meaning. This poses a significant challenge for improving the evaluation results and alignment of vision-language models. To address this challenge, this paper evaluates the combination of paraphrasing and negation, proposes a new CLIP contrastive loss function accounting for both paraphrasing and negation, and applies LLM-generated training triples consisting of original, paraphrased and negated textual captions to CLIP-like training models. The approach, called SemCLIP, is shown to move paraphrased captions towards the original image embeddings while pushing negated captions further away in embedding space. Empirically, SemCLIP is shown to be capable of preserving CLIP's performance while increasing considerably the distances to negated captions. On the CC-Neg benchmark using an original over negation image-retrieval accuracy metric, SemCLIP improves accuracy from 68.1% to 78.1%. Although results are mixed when compared with CLIP on the Sugarcrepe++ benchmark, SemCLIP's performance is generally better than the models trained with negated captions. This robustness to negation extends to downstream zero-shot classification tasks where SemCLIP pre-trained on Sugarcrepe++ performs better than CLIP on all tested downstream tasks. These results indicate that SemCLIP can achieve significant robustness to semantic transformations.

Q1 For what purpose was the dataset created? Q2 Who created the dataset (e.g., which team, research group) and on behalf of which Q3 Who funded the creation of the dataset? Q1 What do the instances that comprise the dataset represent (e.g., documents, photos, Are there multiple types of instances (e.g., movies, users, and ratings; Is the sample representative of the larger set (e.g., geographic coverage)? Q4 What data does each instance consist of? In either case, please provide a description.

Vision-language models (VLMs), such as CLIP, have demonstrated strong performance across a range of downstream tasks. However, CLIP is still limited in negation understanding: the ability to recognize the absence or exclusion of a concept. Existing methods address the problem by using a large language model (LLM) to generate large-scale data of image captions containing negation for further fine-tuning CLIP. However, these methods are both time- and compute-intensive, and their evaluations are typically restricted to image-text matching tasks. To expand the horizon, we (1) introduce a training-time negation data generation pipeline such that negation captions are generated during the training stage, which only increases 2.5% extra training time, and (2) we propose the first benchmark, Neg-TtoI, for evaluating text-to-image generation models on prompts containing negation, assessing model's ability to produce semantically accurate images. We show that our proposed method, TNG-CLIP, achieves SOTA performance on diverse negation benchmarks of image-to-text matching, text-to-image retrieval, and image generation.

Incorporating automatically predicted human feedback into the process of training generative models has attracted substantial recent interest, while feedback at inference time has received less attention. The typical feedback at training time, i.e., preferences of choice given two samples, does not naturally transfer to the inference phase. We introduce a novel type of feedback -- caption reformulations -- and train models to mimic reformulation feedback based on human annotations. Our method does not require training the image captioning model itself, thereby demanding substantially less computational effort. We experiment with two types of reformulation feedback: first, we collect a dataset of human reformulations that correct errors in the generated captions. We find that incorporating reformulation models trained on this data into the inference phase of existing image captioning models results in improved captions, especially when the original captions are of low quality. We apply our method to non-English image captioning, a domain where robust models are less prevalent, and gain substantial improvement. Second, we apply reformulations to style transfer. Quantitative evaluations reveal state-of-the-art performance on German image captioning and English style transfer, while human validation with a detailed comparative framework exposes the specific axes of improvement.

Compositional reasoning in Vision-Language Models (VLMs) remains challenging as these models often struggle to relate objects, attributes, and spatial relationships. Recent methods aim to address these limitations by relying on the semantics of the textual description, using Large Language Models (LLMs) to break them down into subsets of questions and answers. However, these methods primarily operate on the surface level, failing to incorporate deeper lexical understanding while introducing incorrect assumptions generated by the LLM. In response to these issues, we present Caption Expansion with Contradictions and Entailments (CECE), a principled approach that leverages Natural Language Inference (NLI) to generate entailments and contradictions from a given premise. CECE produces lexically diverse sentences while maintaining their core meaning. Through extensive experiments, we show that CECE enhances interpretability and reduces overreliance on biased or superficial features. By balancing CECE along the original premise, we achieve significant improvements over previous methods without requiring additional fine-tuning, producing state-of-the-art results on benchmarks that score agreement with human judgments for image-text alignment, and achieving an increase in performance on Winoground of +19.2% (group score) and +12.9% on EqBen (group score) over the best prior work (finetuned with targeted data).