Vered Shwartz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Vered Shwartz has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
- Sahithya Ravi
University of British Columbia
7 shared publications - EunJeong Hwang
University of British Columbia
4 shared publications - Leonid Sigal
University of British Columbia
4 shared publications Raymond Ng
University of British Columbia
4 shared publications- Ido Dagan
Bar-Ilan University
3 shared publications - Mehar Bhatia
University of British Columbia Vector Institute for AI
3 shared publications
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8962-8966
A Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System
Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not well equipped to evaluate. Surveillance frames, dashcam stills, and phone photographs may be used to establish presence, sequence, causation, damage, or identity, yet contemporary generative systems allow non-experts to alter or fabricate such images through ordinary prompt-based interfaces. Existing image-forensics benchmarks provide important resources for face manipulation, classical tampering, and general synthetic-image detection, but they are not organized around the forms of visual evidence submitted in courts, the localized edits that can change what an exhibit appears to prove, or the consumer-tool threat model now facing the justice system. We introduce the CIFAR Synthetic Evidence Corpus for Detecting AI-Manipulated Images, a benchmark for evidentiary image authentication in court and justice-system contexts. The corpus contains 1,505 photographic items, including 720 authentic controls and 785 manipulated or fabricated images, spanning surveillance, dashcam, and consumer-photo imagery. Manipulations are organized into scene-condition edits, localized element edits, and full fabrications produced with contemporary generative systems. Each item is released with structured metadata covering source provenance, manipulation tier, subtype, generator, prompt template, and scene attributes, enabling controlled evaluation beyond aggregate binary detection. We also establish state-of-the-art baselines with publicly available image-manipulation detectors, showing that current systems exhibit error profiles that remain problematic for evidentiary use. The dataset, prompts, metadata manifest, code, and baseline evaluation scripts are released to support research on visual evidence authentication, information integrity, and trustworthy AI for the justice system.
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8962-8966
Open AccessA Benchmark & Dataset for Detecting AI-Manipulated Visual Evidence in the Court System
Photographic evidence is becoming increasingly vulnerable to forms of alteration and fabrication that existing legal and technical workflows are not well equipped to evaluate. Surveillance frames, dashcam stills, and phone photographs may be used to establish presence, sequence, causation, damage, or identity, yet contemporary generative systems allow non-experts to alter or fabricate such images through ordinary prompt-based interfaces. Existing image-forensics benchmarks provide important resources for face manipulation, classical tampering, and general synthetic-image detection, but they are not organized around the forms of visual evidence submitted in courts, the localized edits that can change what an exhibit appears to prove, or the consumer-tool threat model now facing the justice system. We introduce the CIFAR Synthetic Evidence Corpus for Detecting AI-Manipulated Images, a benchmark for evidentiary image authentication in court and justice-system contexts. The corpus contains 1,505 photographic items, including 720 authentic controls and 785 manipulated or fabricated images, spanning surveillance, dashcam, and consumer-photo imagery. Manipulations are organized into scene-condition edits, localized element edits, and full fabrications produced with contemporary generative systems. Each item is released with structured metadata covering source provenance, manipulation tier, subtype, generator, prompt template, and scene attributes, enabling controlled evaluation beyond aggregate binary detection. We also establish state-of-the-art baselines with publicly available image-manipulation detectors, showing that current systems exhibit error profiles that remain problematic for evidentiary use. The dataset, prompts, metadata manifest, code, and baseline evaluation scripts are released to support research on visual evidence authentication, information integrity, and trustworthy AI for the justice system.
- 22 September 2026
- Published by Springer Nature
- p. 1-17
Spotlight: Identifying and Localizing Video Generation Errors Using VLMs
- 22 September 2026
- Published by Springer Nature
- p. 1-17
Spotlight: Identifying and Localizing Video Generation Errors Using VLMs
- Open Access
- 25 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 421-429
Quantifying Media Representation Dynamics Across 25 Years of News Reporting on Policing-related Deaths
- 25 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 421-429
Open AccessQuantifying Media Representation Dynamics Across 25 Years of News Reporting on Policing-related Deaths
- Open Access
SPIKE-RL: Video-LLMs meet Bayesian Surprise
Real-world videos often show routine activities punctuated by memorable, surprising events. However, most Video-LLMs process videos by sampling frames uniformly, likely missing critical moments that define a video's narrative. We introduce SPIKE, an inference-time framework that quantifies Bayesian Surprise as the belief update triggered by new visual evidence in the video stream, identifying moments where new visual evidence conflicts with prior beliefs. SPIKE effectively localizes surprise in videos, strongly correlated with humans on positive (FunQA) and negative (Oops!) surprise benchmarks. Since the beliefs of zero-shot Video-LLMs are often suboptimal, we develop SPIKE-RL, which leverages GRPO to optimize belief hypotheses based on a reward signal from the video caption. SPIKE and SPIKE-RL guide query-agnostic surprise-weighted frame sampling, which allocates more frames to interesting moments in the video. With this strategy, we achieve consistent performance gains on five downstream benchmarks over uniform sampling. By enabling Video-LLMs to track beliefs and register surprise, our work paves the way for more robust models that can revise their understanding in response to new information.
Open AccessSPIKE-RL: Video-LLMs meet Bayesian Surprise
Real-world videos often show routine activities punctuated by memorable, surprising events. However, most Video-LLMs process videos by sampling frames uniformly, likely missing critical moments that define a video's narrative. We introduce SPIKE, an inference-time framework that quantifies Bayesian Surprise as the belief update triggered by new visual evidence in the video stream, identifying moments where new visual evidence conflicts with prior beliefs. SPIKE effectively localizes surprise in videos, strongly correlated with humans on positive (FunQA) and negative (Oops!) surprise benchmarks. Since the beliefs of zero-shot Video-LLMs are often suboptimal, we develop SPIKE-RL, which leverages GRPO to optimize belief hypotheses based on a reward signal from the video caption. SPIKE and SPIKE-RL guide query-agnostic surprise-weighted frame sampling, which allocates more frames to interesting moments in the video. With this strategy, we achieve consistent performance gains on five downstream benchmarks over uniform sampling. By enabling Video-LLMs to track beliefs and register surprise, our work paves the way for more robust models that can revise their understanding in response to new information.
- Open Access
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking. Importantly, we go significantly beyond the current benchmarks, which simply measure the final performance of VLM response, by also comparing and contrasting it to the performance of probes trained directly on features obtained from the visual encoder, intermediate vision-language projection and LLM-decoder output. In doing so, we uncover shortcomings in VLMs and make a number of important observations about their capabilities, robustness and how they process visual information. We hope our insights will guide progress in further improving VLMs.
Open AccessResponse Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Vision-language Models (VLMs) have emerged as general-purpose tools for addressing a variety of complex computer vision problems. Such models have been shown to be highly capable, but, at the same time, lacking some basic visual understanding skills. In this paper, we set out to understand the limitations of SoTA VLMs on fundamental visual tasks by constructing a series of tests that probe which components of design, specifically, may be lacking. Importantly, we go significantly beyond the current benchmarks, which simply measure the final performance of VLM response, by also comparing and contrasting it to the performance of probes trained directly on features obtained from the visual encoder, intermediate vision-language projection and LLM-decoder output. In doing so, we uncover shortcomings in VLMs and make a number of important observations about their capabilities, robustness and how they process visual information. We hope our insights will guide progress in further improving VLMs.
- Open Access
Is It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4
LLMs have been demonstrated to align with the values of Western or North American cultures. Prior work predominantly showed this effect through leveraging surveys that directly ask (originally people and now also LLMs) about their values. However, it is hard to believe that LLMs would consistently apply those values in real-world scenarios. To address that, we take a bottom-up approach, asking LLMs to reason about cultural norms in narratives from different cultures. We find that GPT-4 tends to generate norms that, while not necessarily incorrect, are significantly less culture-specific. In addition, while it avoids overtly generating stereotypes, the stereotypical representations of certain cultures are merely hidden rather than suppressed in the model, and such stereotypes can be easily recovered. Addressing these challenges is a crucial step towards developing LLMs that fairly serve their diverse user base.
Open AccessIs It Bad to Work All the Time? Cross-Cultural Evaluation of Social Norm Biases in GPT-4
LLMs have been demonstrated to align with the values of Western or North American cultures. Prior work predominantly showed this effect through leveraging surveys that directly ask (originally people and now also LLMs) about their values. However, it is hard to believe that LLMs would consistently apply those values in real-world scenarios. To address that, we take a bottom-up approach, asking LLMs to reason about cultural norms in narratives from different cultures. We find that GPT-4 tends to generate norms that, while not necessarily incorrect, are significantly less culture-specific. In addition, while it avoids overtly generating stereotypes, the stereotypical representations of certain cultures are merely hidden rather than suppressed in the model, and such stereotypes can be easily recovered. Addressing these challenges is a crucial step towards developing LLMs that fairly serve their diverse user base.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 25530-25545
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N. Balasubramanian, Leonid Sigal. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 25530-25545
Open AccessResponse Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities
Shivam Chandhok, Wan-Cyuan Fan, Vered Shwartz, Vineeth N. Balasubramanian, Leonid Sigal. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 22611-22632
BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle
EunJeong Hwang, Peter West, Vered Shwartz. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 22611-22632
Open AccessBottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle
EunJeong Hwang, Peter West, Vered Shwartz. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning
Social media platforms are rich sources of opinionated content. Stance detection allows the automatic extraction of users' opinions on various topics from such content. We focus on zero-shot stance detection, where the model's success relies on (a) having knowledge about the target topic; and (b) learning general reasoning strategies that can be employed for new topics. We present Stance Reasoner, an approach to zero-shot stance detection on social media that leverages explicit reasoning over background knowledge to guide the model's inference about the document's stance on a target. Specifically, our method uses a pre-trained language model as a source of world knowledge, with the chain-of-thought in-context learning approach to generate intermediate reasoning steps. Stance Reasoner outperforms the current state-of-the-art models on 3 Twitter datasets, including fully supervised models. It can better generalize across targets, while at the same time providing explicit and interpretable explanations for its predictions.
Open AccessStance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning
Social media platforms are rich sources of opinionated content. Stance detection allows the automatic extraction of users' opinions on various topics from such content. We focus on zero-shot stance detection, where the model's success relies on (a) having knowledge about the target topic; and (b) learning general reasoning strategies that can be employed for new topics. We present Stance Reasoner, an approach to zero-shot stance detection on social media that leverages explicit reasoning over background knowledge to guide the model's inference about the document's stance on a target. Specifically, our method uses a pre-trained language model as a source of world knowledge, with the chain-of-thought in-context learning approach to generate intermediate reasoning steps. Stance Reasoner outperforms the current state-of-the-art models on 3 Twitter datasets, including fully supervised models. It can better generalize across targets, while at the same time providing explicit and interpretable explanations for its predictions.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 6763-6782
From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models
Mehar Bhatia, Sahithya Ravi, Aditya Chinchure, EunJeong Hwang, Vered Shwartz. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 6763-6782
Open AccessFrom Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models
Mehar Bhatia, Sahithya Ravi, Aditya Chinchure, EunJeong Hwang, Vered Shwartz. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.