Papers
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Steps
Martin Tutek, Fateme Hashemi Chaleshtori, Ana Marasovic et al.
Enhancing LLM Text Detection with Retrieved Contexts and Logits Distribution Consistency
Zhaoheng Huang, Yutao Zhu, Ji-Rong Wen et al.
CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models
Kairong Han, Wenshuo Zhao, Ziyu Zhao et al.
AI Knows Where You Are: Exposure, Bias, and Inference in Multimodal Geolocation with KoreaGEO
Xiaonan Wang, Bo Shao, Hansaem Kim
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance
Yao Wang, Di Liang, Minlong Peng
RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models
Zhaoyan Gong, Juan Li, Zhiqiang Liu et al.
Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Search
Weicong Qin, Yi Xu, Weijie Yu et al.
Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment
Tong Zhang, Kuofeng Gao, Jiawang Bai et al.
ICR: Iterative Clarification and Rewriting for Conversational Search
Zhiyu Cao, Peifeng Li, Qiaoming Zhu
DINT Transformer
Yueyang Cang, Yuhang Liu, Xiaoteng Zhang et al.
XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
Haoqi Yang, Yao Yao, Zuchao Li et al.
CR4-NarrEmote: An Open Vocabulary Dataset of Narrative Emotions Derived Using Citizen Science
Andrew Piper, Robert Budac
CROP: Contextual Region-Oriented Visual Token Pruning
Jiawei Guo, Feifei Zhai, Pu Jian et al.
UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment
Joseph Marvin Imperial, Abdullah Barayan, Regina Stodden et al.
Language models can learn implicit multi-hop reasoning, but only if they have lots of training data
Yuekun Yao, Yupei Du, Dawei Zhu et al.
CodeArena: Evaluating and Aligning CodeLLMs on Human Preference
Jian Yang, Jiaxi Yang, Wei Zhang et al.
Can Large Language Models Win the International Mathematical Games?
Alessio Cocchieri, Luca Ragazzi, Giuseppe Tagliavini et al.
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection
Miao Ziqi, Yi Ding, Lijun Li et al.
Generative or Discriminative? Revisiting Text Classification in the Era of Transformers
Siva Rajesh Kasa, Karan Gupta, Sumegh Roychowdhury et al.
Reimagining Safety Alignment with An Image
Yifan Xia, Guorui Chen, Wenqian Yu et al.
TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making
Kechen Jiao, Zhirui Fang, Jiahao Liu et al.
Plan Dynamically, Express Rhetorically: A Debate-Driven Rhetorical Framework for Argumentative Writing
Xueguan Zhao, Wenpeng Lu, Chaoqun Zheng et al.
Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey
Mehrab Tanjim, Yeonjun In, Xiang Chen et al.
Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
Dawid Jan Kopiczko, Tijmen Blankevoort, Yuki M Asano
Token-Aware Editing of Internal Activations for Large Language Model Alignment
Tianbo Wang, Yuqing Ma, Kewei Liao et al.