32 citations · 202 across the 82 of their papers we have counts for
14 papers · 1 filter
Investigating The Functional Roles of Attention Heads in Vision Language Models: Evidence for Reasoning Modules
Yanbei Jiang, Xueqi Ma, Shu Liu +5
Despite excelling on multimodal benchmarks, vision-language models (VLMs) largely remain a black box. In this paper, we propose a novel interpretability framework to systematically…
PROPA: Toward Process-level Optimization in Visual Reasoning via Reinforcement Learning
Yanbei Jiang, Chao Lei, Yihao Ding +2
Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the re…
Reasoning Like Experts: Leveraging Multimodal Large Language Models for Drawing-based Psychoanalysis
Xueqi Ma, Yanbei Jiang, Sarah Erfani +4
Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance across various objective multimodal perception tasks, yet their application to subjective, emotio…
Understanding the Geospatial Reasoning Capabilities of LLMs: A Trajectory Recovery Perspective
Thinh Hung Truong, Jey Han Lau, Jianzhong Qi
We explore the geospatial reasoning capabilities of Large Language Models (LLMs), specifically, whether LLMs can read road network maps and perform navigation. We frame trajectory…
COMMUNITYNOTES: A Dataset for Exploring the Helpfulness of Fact-Checking Explanations
Rui Xing, Preslav Nakov, Timothy Baldwin +1
Fact-checking on major platforms, such as X, Meta, and TikTok, is shifting from expert-driven verification to a community-based setup, where users contribute explanatory notes to c…
On the Interplay between Human Label Variation and Model Fairness
Kemal Kurniawan, Meladel Mistica, Timothy Baldwin +1
The impact of human label variation (HLV) on model fairness is an unexplored topic. This paper examines the interplay by comparing training on majority-vote labels with a range of…
Beyond Perception: Evaluating Abstract Visual Reasoning through Multi-Stage Task
Yanbei Jiang, Yihao Ding, Chao Lei +3
Current Multimodal Large Language Models (MLLMs) excel in general visual reasoning but remain underexplored in Abstract Visual Reasoning (AVR), which demands higher-order reasoning…
FLUKE: A Linguistically-Driven and Task-Agnostic Framework for Robustness Evaluation
Yulia Otmakhova, Hung Thinh Truong, Rahmad Mahendra +4
We present FLUKE (Framework for LingUistically-driven and tasK-agnostic robustness Evaluation), a framework for assessing model robustness through systematic minimal variations of…
Moderation Matters:Measuring Conversational Moderation Impact in English as a Second Language Group Discussion
Rena Gao, Ming-Bin Chen, Lea Frermann +1
English as a Second Language (ESL) speakers often struggle to engage in group discussions due to language barriers. While moderators can facilitate participation, few studies asses…
Can LLMs Simulate L2-English Dialogue? An Information-Theoretic Analysis of L1-Dependent Biases
Rena Gao, Xuetong Wu, Tatsuki Kuribayashi +6
This study evaluates Large Language Models' (LLMs) ability to simulate non-native-like English use observed in human second language (L2) learners interfered with by their native f…
An Analytical Emotion Framework of Rumour Threads on Social Media
Rui Xing, Boyang Sun, Kun Zhang +3
Rumours in online social media pose significant risks to modern society, motivating the need for better understanding of how they develop. We focus specifically on the interface be…
Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
Shengxiang Gao, Jey Han Lau, Jianzhong Qi
Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with uns…
Training and Evaluating with Human Label Variation: An Empirical Study
Kemal Kurniawan, Meladel Mistica, Timothy Baldwin +1
Human label variation (HLV) challenges the standard assumption that a labelled instance has a single ground truth, instead embracing the natural variation in human annotation to tr…
Decomposed Opinion Summarization with Verified Aspect-Aware Modules
Miao Li, Jey Han Lau, Eduard Hovy +1
Opinion summarization plays a key role in deriving meaningful insights from large-scale online reviews. To make the process more explainable and grounded, we propose a domain-agnos…