Canlyniadau Chwilio - Ramachandran, Deepak

Understanding Finetuning for Factual Knowledge Extraction from Language Models gan Kazemi, Mehran, Mittal, Sid, Ramachandran, Deepak

Cael y testun llawn
Cael y testun llawn

Prompt Expansion for Adaptive Text-to-Image Generation gan Datta, Siddhartha, Ku, Alexander, Ramachandran, Deepak, Anderson, Peter

Cael y testun llawn
Cael y testun llawn

e-COP : Episodic Constrained Optimization of Policies gan Agnihotri, Akhil, Jain, Rahul, Ramachandran, Deepak, Singla, Sahil

Cael y testun llawn
Cael y testun llawn

Online Bandit Learning with Offline Preference Data for Improved RLHF gan Agnihotri, Akhil, Jain, Rahul, Ramachandran, Deepak, Wen, Zheng

Cael y testun llawn
Cael y testun llawn

Best Policy Learning from Trajectory Preference Feedback gan Agnihotri, Akhil, Jain, Rahul, Ramachandran, Deepak, Wen, Zheng

Cael y testun llawn
Cael y testun llawn

Multi-Objective Preference Optimization: Improving Human Alignment of Generative Models gan Agnihotri, Akhil, Jain, Rahul, Ramachandran, Deepak, Wen, Zheng

Cael y testun llawn
Cael y testun llawn

Which Linguist Invented the Lightbulb? Presupposition Verification for Question-Answering gan Kim, Najoung, Pavlick, Ellie, Ayan, Burcu Karagol, Ramachandran, Deepak

Cael y testun llawn
Cael y testun llawn

Do Language Embeddings Capture Scales? gan Zhang, Xikun, Ramachandran, Deepak, Tenney, Ian, Elazar, Yanai, Roth, Dan

Cael y testun llawn
Cael y testun llawn

LAMBADA: Backward Chaining for Automated Reasoning in Natural Language gan Kazemi, Mehran, Kim, Najoung, Bhatia, Deepti, Xu, Xin, Ramachandran, Deepak

Cael y testun llawn
Cael y testun llawn

TaskLAMA: Probing the Complex Task Understanding of Language Models gan Yuan, Quan, Kazemi, Mehran, Xu, Xin, Noble, Isaac, Imbrasaite, Vaiva, Ramachandran, Deepak

Cael y testun llawn
Cael y testun llawn

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization gan Xu, Zaiyan, Vemuri, Sushil, Panaganti, Kishan, Kalathil, Dileep, Jain, Rahul, Ramachandran, Deepak

Cael y testun llawn
Cael y testun llawn

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information gan Kazemi, Mehran, Yuan, Quan, Bhatia, Deepti, Kim, Najoung, Xu, Xin, Imbrasaite, Vaiva, Ramachandran, Deepak

Cael y testun llawn
Cael y testun llawn

Tackling Provably Hard Representative Selection via Graph Neural Networks gan Kazemi, Mehran, Tsitsulin, Anton, Esfandiari, Hossein, Bateni, MohammadHossein, Ramachandran, Deepak, Perozzi, Bryan, Mirrokni, Vahab

Cael y testun llawn
Cael y testun llawn

Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic gan Pryor, Connor, Yuan, Quan, Liu, Jeremiah, Kazemi, Mehran, Ramachandran, Deepak, Bedrax-Weiss, Tania, Getoor, Lise

Cael y testun llawn
Cael y testun llawn

Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play gan Liu, Jeremiah Zhe, Dvijotham, Krishnamurthy Dj, Lee, Jihyeon, Yuan, Quan, Strobel, Martin, Lakshminarayanan, Balaji, Ramachandran, Deepak

Cael y testun llawn
Cael y testun llawn

Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers gan Wang, Haoyu, Song, Yuliang, Li, Tao, Deng, Zhiwei, Wang, Yaqing, Ramachandran, Deepak, Cohen, Eldan, Roth, Dan

Cael y testun llawn
Cael y testun llawn

Preference Adaptive and Sequential Text-to-Image Generation gan Nabati, Ofir, Tennenholtz, Guy, Hsu, ChihWei, Ryu, Moonkyung, Ramachandran, Deepak, Chow, Yinlam, Li, Xiang, Boutilier, Craig

Cael y testun llawn
Cael y testun llawn

Modeling subjectivity (by Mimicking Annotator Annotation) in toxic comment identification across diverse communities gan Dutta, Senjuti, Mittal, Sid, Chen, Sherol, Ramachandran, Deepak, Rajakumar, Ravi, Kivlichan, Ian, Mak, Sunny, Butryna, Alena, Paritosh, Praveen

Cael y testun llawn
Cael y testun llawn

Demystifying Embedding Spaces using Large Language Models gan Tennenholtz, Guy, Chow, Yinlam, Hsu, Chih-Wei, Jeong, Jihwan, Shani, Lior, Tulepbergenov, Azamat, Ramachandran, Deepak, Mladenov, Martin, Boutilier, Craig

Cael y testun llawn
Cael y testun llawn

FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue gan Albalak, Alon, Tuan, Yi-Lin, Jandaghi, Pegah, Pryor, Connor, Yoffe, Luke, Ramachandran, Deepak, Getoor, Lise, Pujara, Jay, Wang, William Yang

Cael y testun llawn
Cael y testun llawn