2 citations · 4 across the 6 of their papers we have counts for
7 papers · 1 filter
How Robust Is Multimodal Claim Verification to LLM Rewriting?
Yun-Ang Wu, Xanh Ho, Andre Greiner-Petter +4
LLMs are known to introduce stylistic changes into generated text, yet how these stylistic shifts affect model decisions on scientific tasks remains underexplored. In this paper, w…
Last Translation Benchmark
Vilém Zouhar, Niyati Bafna, Mukund Choudhary +263
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, stan…
Encoded but Not Routed: Explaining the Table-Chart Gap in Scientific Claim Verification
Sunisth Kumar, Xanh Ho, Tim Schopf +3
Multimodal LLMs are increasingly used to assist scientific peer review, where a core requirement is verifying whether claims in a paper are supported by its evidence. Prior work ha…
SciClaimEval: Cross-modal Claim Verification in Scientific Papers
Xanh Ho, Yun-Ang Wu, Sunisth Kumar +4
We present SciClaimEval, a new scientific dataset for the claim verification task. Unlike existing resources, SciClaimEval features authentic claims, including refuted ones, direct…
Format Matters: The Robustness of Multimodal LLMs in Reviewing Evidence from Tables and Charts
Xanh Ho, Yun-Ang Wu, Sunisth Kumar +3
With the growing number of submitted scientific papers, there is an increasing demand for systems that can assist reviewers in evaluating research claims. Experimental results are…
Table-Text Alignment: Explaining Claim Verification Against Tables in Scientific Papers
Xanh Ho, Sunisth Kumar, Yun-Ang Wu +3
Scientific claim verification against tables typically requires predicting whether a claim is supported or refuted given a table. However, we argue that predicting the final label…
Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages
Sunisth Kumar, Davide Liu, Alexandre Boulenger
We propose an efficient modeling framework for cross-lingual named entity recognition in semi-structured text data. Our approach relies on both knowledge distillation and consisten…