Papers by Yanda Li
Reason from Fallacy: Enhancing Large Language Models’ Logical Reasoning through Logical Fallacy Understanding (2024.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated good performance in many reasoning tasks, but struggle with some more complex reasoning tasks including logical reasoning. |
| Approach: | They propose five concrete tasks from three cognitive dimensions of WHAT, WHY, and HOW to evaluate LLMs’ capability of logical fallacy understanding. |
| Outcome: | The proposed dataset can be used to evaluate LLMs’ LFU capability and to fine-tune LLM models to obtain significantly enhanced performance on logical reasoning. |
MTPChat: A Multimodal Time-Aware Persona Dataset for Conversational Agents (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing time-aware datasets that focus on persona-grounded conversations focus on temporal dynamics, which narrows their scope and diminishes their complexity. |
| Approach: | They propose a multimodal, time-aware persona dialogue dataset that integrates linguistic, visual, and temporal elements within dialogue and persona memory. |
| Outcome: | The proposed framework integrates linguistic, visual, and temporal elements within dialogue and persona memory to assess a model’s ability to understand implicit temporal cues and dynamic interactions. |
Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Large audio-language models (LALMs) can exhibit a temporal smoothing bias . unified decoders can produce less specific audio-grounded outputs . |
| Approach: | They propose a temporally blurred slow-path view that is re-encoded by a token-level logit update. |
| Outcome: | Experiments on MMAU and AIR-Bench show consistent improvements on strong unified LALMs. |
Who Can Withstand Chat-Audio Attacks? An Evaluation Benchmark for Large Audio-Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing research focused on model-specific adversarial methods, but real-world applications demand a more generalizable approach to audio adversarials. |
| Approach: | They propose a Chat-Audio Attacks benchmark to evaluate LALMs' robustness . they propose standard evaluation, GPT-4o-based evaluation and human evaluation . |
| Outcome: | The proposed benchmark aims to explore the robustness of six state-of-the-art LALMs with voice interaction capabilities. |
Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data (2024.findings-acl)
Copied to clipboard
Yanda Li, Chi Zhang, Gang Yu, Wanqi Yang, Zhibin Wang, Bin Fu, Guosheng Lin, Chunhua Shen, Ling Chen, Yunchao Wei
| Challenge: | OpenAI's GPT-4 has demonstrated remarkable multimodal capabilities, but specific mechanics of GPT4 remain unknown. |
| Approach: | They propose a data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. |
| Outcome: | The proposed method improves on ten commonly assessed models and provides greater flexibility compared to existing methods. |
Enhancing Temporal Sensitivity and Reasoning for Time-Sensitive Question Answering (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing language models have limited sensitivity to temporal information and inadequate temporal reasoning capabilities. |
| Approach: | They propose a framework that enhances temporal awareness and reasoning . they propose to use Temporal Information-Aware Embedding and Granular Contrastive Reinforcement Learning . |
| Outcome: | The proposed framework outperforms existing LLMs on time-sensitive question answering tasks. |