English
Related papers

Related papers: Enhancing Multi-Domain Automatic Short Answer Grad…

200 papers

Recent advances in natural language processing highlight two key factors for improving reasoning in large language models (LLMs): (i) allocating more test-time compute tends to help on harder problems but often introduces redundancy in the…

Computation and Language · Computer Science 2025-11-04 Riccardo Alberghi , Elizaveta Demyanenko , Luca Biggio , Luca Saglietti

Symbolic Regression (SR) plays a central role in scientific knowledge discovery by distilling mathematical equations from observational data. Most existing SR methods function within a bi-level optimization framework: an outer loop that…

Machine Learning · Computer Science 2026-05-25 Boxiao Wang , Kai Li , Zhiwei Chen , Yang Huang , Runxiang Wang , Ziwen Zhang , Yifan Zhang , Jian Cheng

Recent advances in Large Language Models have demonstrated their capabilities across a variety of tasks. However, automatically extracting implicit knowledge from natural language remains a significant challenge, as machines lack active…

Artificial Intelligence · Computer Science 2026-03-06 Anna Sofia Lippolis , Andrea Giovanni Nuzzolese , Aldo Gangemi

Large-scale high-quality training data is important for improving the performance of models. After trained with data that has rationales (reasoning steps), models gain reasoning capability. However, the dataset with high-quality rationales…

Computation and Language · Computer Science 2024-05-01 Yunlong Feng , Yang Xu , Libo Qin , Yasheng Wang , Wanxiang Che

Monitoring and analyzing process traces is a critical task for modern companies and organizations. In scenarios where there is a gap between trace events and reference business activities, this entails an interpretation problem, amounting…

Artificial Intelligence · Computer Science 2026-05-26 Bettina Fazzinga , Sergio Flesca , Filippo Furfaro , Luigi Pontieri , Francesco Scala

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and…

Computer Vision and Pattern Recognition · Computer Science 2024-06-14 Weizhao He , Yang Zhang , Wei Zhuo , Linlin Shen , Jiaqi Yang , Songhe Deng , Liang Sun

Explainable AI (XAI) in high-stakes domains should help stakeholders trust and verify system outputs. Yet Chain-of-Thought methods reason before concluding, and logical gaps or hallucinations can yield conclusions that do not reliably align…

Artificial Intelligence · Computer Science 2026-01-13 Chen Qian , Yimeng Wang , Yu Chen , Lingfei Wu , Andreas Stathopoulos

Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewards are primarily confined to guiding the final localization,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Tao Yang , Qing Zhou , Yanliang Li , Qi Wang

Current multimodal models often suffer from shallow reasoning, leading to errors caused by incomplete or inconsistent thought processes. To address this limitation, we propose Self-Verification and Self-Rectification (SVSR), a unified…

Artificial Intelligence · Computer Science 2026-05-29 Zhe Qian , Nianbing Su , Zhonghua Wang , Hebei Li , Zhongxing Xu , Yueying Li , Fei Luo , Zhuohan Ouyang , Yanbiao Ma

Automated scoring of students' scientific explanations offers the potential for immediate, accurate feedback, yet class imbalance in rubric categories particularly those capturing advanced reasoning remains a challenge. This study…

Artificial Intelligence · Computer Science 2026-04-23 Prudence Djagba , Kevin Haudek , Clare G. C. Franovic , Leonora Kaldaras

Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing specific tasks. Additionally, it has been shown that model performance…

Computation and Language · Computer Science 2025-12-19 Nikhil Prakash , Donghao Ren , Dominik Moritz , Yannick Assogba

Reasoning in Large Language Models (LLMs) poses a challenge for oversight as many misaligned behaviors do not surface until reasoning concludes. To address this, we introduce Behavior Cue Reasoning for making LLM reasoning more controllable…

Artificial Intelligence · Computer Science 2026-05-21 Christopher Z. Cui , Taylor W. Killian , Prithviraj Ammanabrolu

Answering compositional questions that require multiple steps of reasoning against text is challenging, especially when they involve discrete, symbolic operations. Neural module networks (NMNs) learn to parse such questions as executable…

Computation and Language · Computer Science 2020-02-18 Nitish Gupta , Kevin Lin , Dan Roth , Sameer Singh , Matt Gardner

Rationalization empowers deep learning models with self-explaining capabilities through a cooperative game, where a generator selects a semantically consistent subset of the input as a rationale, and a subsequent predictor makes predictions…

Artificial Intelligence · Computer Science 2023-12-18 Wei Liu , Haozhao Wang , Jun Wang , Zhiying Deng , YuanKai Zhang , Cheng Wang , Ruixuan Li

Prediction without justification has limited applicability. As a remedy, we learn to extract pieces of input text as justifications -- rationales -- that are tailored to be short and coherent, yet sufficient for making the same prediction.…

Computation and Language · Computer Science 2016-11-04 Tao Lei , Regina Barzilay , Tommi Jaakkola

Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems. While…

Artificial Intelligence · Computer Science 2026-05-01 Adam Ishay , Joohyung Lee

Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer…

A class of explainable NLP models for reasoning tasks support their decisions by generating free-form or structured explanations, but what happens when these supporting structures contain errors? Our goal is to allow users to interactively…

Computation and Language · Computer Science 2021-04-20 Aman Madaan , Niket Tandon , Dheeraj Rajagopal , Yiming Yang , Peter Clark , Keisuke Sakaguchi , Ed Hovy

Automated grading has become an essential tool in education technology due to its ability to efficiently assess large volumes of student work, provide consistent and unbiased evaluations, and deliver immediate feedback to enhance learning.…

Computers and Society · Computer Science 2025-01-27 Calvin Yeung , Jeff Yu , King Chau Cheung , Tat Wing Wong , Chun Man Chan , Kin Chi Wong , Keisuke Fujii

Training on verifiable symbolic data is a promising way to expand the reasoning frontier of language models beyond what standard pre-training corpora provide. Yet existing procedural generators often rely on fixed puzzles or templates and…

Computation and Language · Computer Science 2026-03-03 Valentin Lacombe , Valentin Quesnel , Damien Sileo