activity
20162026
most citedWhen to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment

26 citations · 112 across the 80 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models

Yijie Tong, Yifan Hou, Shaobo Cui +2

Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their application and benefits for vision-lan…

cs.LG2026

Efficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees

Xueyan Li, Johannes Zenn, Ekaterina Fadeeva +3

Self-consistency boosts inference-time performance by sampling multiple reasoning traces in parallel and voting. However, in constrained domains like math and code, this strategy i…

cs.LG2025

Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs

Xueyan Li, Guinan Su, Mrinmaya Sachan +1

Large Language Models (LLMs) are increasingly applied to complex tasks that require extended reasoning. In such settings, models often benefit from diverse chains-of-thought to arr…

cs.LG2025

Dense SAE Latents Are Features, Not Bugs

Xiaoqing Sun, Alessandro Stolfo, Joshua Engels +4

Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that…

cs.LG2024

MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs

Andreas Opedal, Haruki Shirakami, Bernhard Schölkopf +2

Large language models (LLMs) can solve arithmetic word problems with high accuracy, but little is known about how well they generalize to more complex problems. This is difficult t…

cs.LG20241 cited

Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing

Yilmazcan Ozyurt, Stefan Feuerriegel, Mrinmaya Sachan

Knowledge tracing (KT) is a popular approach for modeling students' learning progress over time, which can enable more personalized and adaptive learning. However, existing KT appr…