1 citations · 1 across the 8 of their papers we have counts for
11 papers
Multi-LLM Collaborative Alignment via Stackelberg Games
Christina Hahn, Shangbin Feng, Dean Light +3
A pool of language models can collaborate and improve collectively by learning from one another's responses. These interactions depend on the instructions used during training. Exi…
Aligned Data Can Induce Misalignment via Context Confusion
Yavuz Bakman, Duygu Nur Yaldiz, Baris Askin +4
Large language models (LLMs) are frequently updated for various use cases, where filtering out misaligned training samples is a common practice for preventing post-update misalignm…
Attention-Aware Routing: Coupling Routing and Attention in MoEs
Despoina Kosmopoulou, Anastasios Tsetsilas, Efthymios Georgiou +3
In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual information. We propose Atte…
EchoPath: Execution-Level Replayable Memory for GUI Agents
Yao Zhao, Aditya Shanmugham, Swastik Roy +1
Computer-use agents increasingly operate browsers, software, and desktop applications via CLI or API portals, but graphical user interface (GUI) still plays an important role in co…
AGC-Bench: Measuring Artificial General Creativity
Roger Beaty, Vijeta Deshpande, Clin K. Y. Lai +9
Creativity research has debated whether creativity is domain-specific (e.g., visual, writing, science), and if it is psychometrically separable from general intelligence. Both ques…
PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges
Swastik Roy, Rajkumar Pujari, Tharindu Kumarage +5
LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rubric asking for a response to be `…
C-MORAL: Controllable Multi-Objective Molecular Optimization with Reinforcement Alignment for LLMs
Rui Gao, Youngseung Jeon, Swastik Roy +2
Large language models (LLMs) show promise for molecular optimization, but aligning them with selective and competing drug-design constraints remains challenging. We propose C-Moral…
ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground Truth
Salman Rahman, Sruthi Gorantla, Arpit Gupta +3
Training process reward models (PRMs) requires step-level correctness labels, obtained either through expensive human annotation or by relying on ground-truth answers, limiting the…
JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation
Zhenyu Bi, Gaurav Srivastava, Yang Li +4
While small language models (SLMs) have shown promise on various reasoning tasks, their ability to judge the correctness of answers remains unclear compared to large language model…
OPTAGENT: Optimizing Multi-Agent LLM Interactions Through Verbal Reinforcement Learning for Enhanced Reasoning
Zhenyu Bi, Meng Lu, Yang Li +4
Large Language Models (LLMs) have shown remarkable reasoning capabilities in mathematical and scientific tasks. To enhance complex reasoning, multi-agent systems have been proposed…
BeyondBench: Contamination-Resistant Evaluation of Reasoning in Language Models
Gaurav Srivastava, Aafiya Hussain, Zhenyu Bi +5
Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce…