COLM 2025 Conference Submissions

SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation
Zichong Li, Chen Liang, Zixuan Zhang, Ilgee Hong, Young Jin Kim, Weizhu Chen, Tuo Zhao
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
SEAM: Semantically Equivalent Across Modalities Benchmark for Vision-Language Models
Zhenwei Tang, Difan Jiao, Blair Yang, Ashton Anderson
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
VideoSAVi: Self-Aligned Video Language Models without Human Supervision
Yogesh Kulkarni, Pooyan Fazli
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Always Tell Me The Odds: Fine-grained Conditional Probability Estimation
Liaoyaqi Wang, Zhengping Jiang, Anqi Liu, Benjamin Van Durme
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
Saaket Agashe, Kyle Wong, Vincent Tu, Jiachen Yang, Ang Li, Xin Eric Wang
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
Hongzhe Du, Weikai Li, Min Cai, Karim Saraipour, Zimin Zhang, Himabindu Lakkaraju, Yizhou Sun, Shichang Zhang
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Implicit In-Context Learning: Evidence from Artificial Language Experiments
Xiaomeng Ma, Qihui Xu
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning
Tian Qin, David Alvarez-Melis, Samy Jelassi, Eran Malach
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
Jacob Dunefsky, Arman Cohan
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
Syrine Belakaria, Joshua Kazdan, Charles Marx, Chris Cundy, Willie Neiswanger, Sanmi Koyejo, Barbara E Engelhardt, Stefano Ermon
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching
Yuxuan Zhu, Ali Falahati, David H. Yang, Mohammad Mohammadi Amiri
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
Li An, Yujian Liu, Yepeng Liu, Yang Zhang, Yuheng Bu, Shiyu Chang
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Do Language Models Agree with Human Perceptions of Suspense in Stories?
Glenn Matlin, Devin Zhang, Rodrigo Barroso Loza, Diana M. Popescu, Joni Isbell, Chandreyi Chakraborty, Mark Riedl
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Learning by Teaching: Engaging Students as Instructors of Large Language Models in Computer Science Education
Xinming Yang, Haasil Pujara, Jun Li
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
CALLME: Call Graph Augmentation with Large Language Models for Javascript
Michael Wang, Kexin Pei, Armando Solar-Lezama
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
Wenhao Zheng, Yixiao Chen, Weitong Zhang, Souvik Kundu, Yun Li, Zhengzhong Liu, Eric P. Xing, Hongyi Wang, Huaxiu Yao
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
LM Agents May Fail to Act on Their Own Risk Knowledge
Yuzhi Tang, Tianxiao Li, Elizabeth Li, Chris J. Maddison, Honghua Dong, Yangjun Ruan
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Approximating Language Model Training Data from Weights
John Xavier Morris, Junjie Oscar Yin, Woojeong Kim, Vitaly Shmatikov, Alexander M Rush
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought'' Control
Hannah Cyberey, David Evans
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Brains vs. Bytes: Evaluating LLM Proficiency in Olympiad Mathematics
Hamed Mahdavi, Alireza Hashemi, Majid Daliri, Pegah Mohammadipour, Alireza Farhadi, Samira Malek, Yekta Yazdanifard, Amir Khasahmadi, Vasant G Honavar
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Hardware-Efficient Attention for Fast Decoding
Ted Zadouri, Hubert Strauss, Tri Dao
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality
Sewoong Lee, Adam Davies, Marc E. Canby, Julia Hockenmaier
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Exploring Large Language Model Agents for Piloting Social Experiments
Jinghua Piao, Yuwei Yan, Nian Li, Jun Zhang, Yong Li
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
In-context Ranking Preference Optimization
Junda Wu, Rohan Surana, Zhouhang Xie, Yiran Shen, Yu Xia, Tong Yu, Ryan A. Rossi, Prithviraj Ammanabrolu, Julian McAuley
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone
Weight ensembling improves reasoning in language models
Xingyu Dang, Christina Baek, Kaiyue Wen, J Zico Kolter, Aditi Raghunathan
- Published: 08 Jul 2025, Last Modified: 26 Aug 2025
- COLM 2025
- Readers: Everyone