5 citations · 40 across the 105 of their papers we have counts for
111 papers
MIC: Explaining Image-Claim Inconsistencies in AI-Generated Multimodal Misinformation
Ruihong Zeng, Jonathan Tonglet, Preslav Nakov +1
Claims paired with AI-generated images are a rapidly growing form of misinformation. Existing automated fact-checking (AFC) methods mainly treat this as a provenance problem, detec…
ReGround: Grounding Reviewer Comments in Multimodal Evidence
Serwar Basch, Lizhen Qu, Iryna Gurevych
Reviewer comments naturally relate to specific parts of the reviewed paper, yet grounding these comments to the underlying evidence is difficult due to long multimodal documents. E…
Learning to Zoom Efficiently with a Contrastive Curriculum
Falko Helm, Iryna Gurevych
Using a zoom-in tool is an important foundational part of modern visual agents, because it allows to efficiently handle tasks involving high-resolution images. Most previous method…
MURANO: Design, Run, and Reproduce Mechanistic Interpretability Experiments as Composable Pipelines
Alireza Bayat Makou, Emirhan Böge, Phu Gia Hoang +5
This paper presents Murano, an open source framework for designing, running, and reproducing mechanistic interpretability studies of large language models, intended for researchers…
Transforming Interactions in Thesis Supervision: An Exposé-First Workflow in Higher Education
Lin-Yin Huang, Dennis Zyska, Iryna Gurevych
At the studied research institute, one professorship oversees approximately 20 theses per semester, while day-to-day supervision is distributed among doctoral and postdoctoral rese…
Parameter Exploration for RLVR via Variational Learning
Vatsal Venkatkrishna, Nico Daheim, Iryna Gurevych
Exploration has been a focus of reinforcement learning research for a long time. Recently, there has been growing evidence that it is also an important ingredient in LLM reinforcem…
OctoLong: Mid-Training On Cross-Repository Code Contexts Enhances Long-Context Modeling
Indraneil Paul, Falko Helm, Goran Glavaš +1
Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflows. However,…
The Boundaries of Automation: A Theory of Persistent Human Participation
Fares Fourati, Hinrich Schütze, Eyke Hüllermeier +1
The rapid progress of AI has intensified the long-standing pursuit of automation: replacing human participation with algorithms wherever possible. Implicit in this pursuit is the a…
The FIL Hypothesis: Inductive Biases Help with Kernel Engineering
Nikolai Rozanov, Subhabrata Dutta, Preslav Nakov +1
The Bitter Lesson, which posits that general-purpose methods that scale with computation and data ultimately outperform those with built-in human knowledge, has become a dominant p…
To Compare, or Not to Compare: On Methodological Practices in Evaluating Social Bias
Federico Marcuzzi, Xuefei Ning, Roy Schwartz +1
As Large Language Models are increasingly deployed in critical applications, robustly evaluating their social biases is paramount. However, the current literature suffers from wide…
Judgment-Grounded Expansion for Peer Review Generation
Sheng Lu, Lizhen Qu, Iryna Gurevych
Automatic review generation is a promising direction for accelerating scientific progress. While most work adopts an end-to-end setup, its fully automated nature makes it less suit…
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
Anmol Goel, Iryna Gurevych
Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-application access is useful, but it also c…
ProReviewer: Evidence-Driven Investigation for Scientific Peer Review
Haishuo Fang, Yue Feng, Iryna Gurevych
Effective peer review requires adaptive investigation that responds to evidence emerging from each paper. Existing LLM-based reviewers largely organize the review process around pr…
ThinkBooster: A Unified Framework for Seamless Test-Time Scaling of LLM Reasoning
Vladislav Smirnov, Chieu Nguyen, Sergey Senichev +14
Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.g., via m…
Contextualized Prompting For Stance Detection On Social Media
Tilman Beck, Shakib Yazdani, Simon Kruschinski +2
Stance detection on social media is challenging due to short, noisy, and context-dependent language. While large language models (LLMs) show zero-shot generalization, they are typi…
'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptions
Nils Dycke, Marina Sakharova, Nico Daheim +1
Although it is generally agreed that AI-generated text poses a broad societal risk, there is no common understanding in the AI-generated text detection literature on what constitut…
Many Circuits, One Mechanism: Input Variation and Evaluation Granularity in Circuit Discovery
Alireza Bayat Makou, Jingcheng Niu, Subhabrata Dutta +1
Circuit discovery methods identify subgraphs that explain model behaviors, and structural differences between discovered circuits are commonly interpreted as evidence of distinct m…
Subjective Code Preferences in Experts and Large Language Models
Anna Mokhova, Subhabrata Dutta, Iryna Gurevych +1
Large Language Models (LLMs) have become increasingly popular for coding tasks, with subjective coding preferences being an essential element to adapt to programmers' personal need…
Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring
Indraneil Paul, Goran Glavaš, Iryna Gurevych
Reward models (RMs) have become an indispensable fixture of the language model (LM) post-training playbook, enabling policy alignment and test-time scaling. Research on the applica…
Co-FactChecker: A Framework for Human-AI Collaborative Claim Verification Using Large Reasoning Models
Dhruv Sahnan, Subhabrata Dutta, Tanmoy Chakraborty +2
Professional fact-checkers rely on domain knowledge and deep contextual understanding to verify claims. Large language models (LLMs) and large reasoning models (LRMs) lack such gro…
ClaimFlow: Tracing the Evolution of Scientific Claims in NLP
Aniket Pramanick, Yufang Hou, Saif M. Mohammad +1
Scientific papers advance that later work supports, extends, or sometimes refutes. Yet existing methods for citation and claim analysis capture only fragments of…
Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale
Jonas Rohweder, Subhabrata Dutta, Iryna Gurevych
Contemporary studies in mechanistic interpretability have uncovered many puzzling phenomena in the neural information processing of Transformer-based language models, such as induc…
Commitment Checklist: Auditing Author Commitments in Peer Review
Chung-Chi Chen, Iryna Gurevych
Peer review author responses often include commitments to add experiments, release code, or clarify content in the final paper. Yet, there is currently no systematic mechanism to e…
Preventing the Collapse of Peer Review Requires Verification-First AI
Lei You, Lele Cao, Iryna Gurevych
This paper argues that AI-assisted peer review should be verification-first rather than review-mimicking. We propose truth-coupling, i.e. how tightly venue scores track latent scie…