English
Related papers

Related papers: Outdated Issue Aware Decoding for Reasoning Questi…

200 papers

Large language models often struggle to recognize their knowledge limits in closed-book question answering, leading to confident hallucinations. While decomposed prompting is typically used to improve accuracy, we investigate its impact on…

Computation and Language · Computer Science 2026-02-05 Dhruv Madhwal , Lyuxin David Zhang , Dan Roth , Tomer Wolfson , Vivek Gupta

Continual learning of new knowledge over time is one desirable capability for intelligent systems to recognize more and more classes of objects. Without or with very limited amount of old data stored, an intelligent system often…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Zhuoyun Li , Changhong Zhong , Sijia Liu , Ruixuan Wang , Wei-Shi Zheng

Over the last couple of decades, there has been a considerable effort devoted to the problem of updating logic programs under the stable model semantics (a.k.a. answer-set programs) or, in other words, the problem of characterising the…

Artificial Intelligence · Computer Science 2022-02-22 João Leite , Martin Slota

Direct Preference Optimization (DPO) has proven effective in complex reasoning tasks like math word problems and code generation. However, when applied to Text-to-SQL datasets, it often fails to improve performance and can even degrade it.…

Computation and Language · Computer Science 2025-02-18 Hanbing Liu , Haoyang Li , Xiaokang Zhang , Ruotong Chen , Haiyong Xu , Tian Tian , Qi Qi , Jing Zhang

Language models (LMs) encode substantial factual knowledge, but often produce answers judged as incorrect. We hypothesize that many of these answers are actually correct, but are expressed in alternative surface forms that are dismissed due…

Computation and Language · Computer Science 2025-09-30 Rajaa El Hamdani , Samy Haffoudhi , Nils Holzenberger , Fabian Suchanek , Thomas Bonald , Fragkiskos D. Malliaros

This paper introduces a novel method for closed information extraction. The method employs a discriminative approach that incorporates type and entity-specific information to improve relation extraction accuracy, particularly benefiting…

Computation and Language · Computer Science 2025-06-23 Cedric Möller , Ricardo Usbeck

When answering a question, humans utilize the information available across different modalities to synthesize a consistent and complete chain of thought (CoT). This process is normally a black box in the case of deep learning models like…

Computation and Language · Computer Science 2022-10-18 Pan Lu , Swaroop Mishra , Tony Xia , Liang Qiu , Kai-Wei Chang , Song-Chun Zhu , Oyvind Tafjord , Peter Clark , Ashwin Kalyan

Data-free knowledge distillation (DFKD) conducts knowledge distillation via eliminating the dependence of original training data, and has recently achieved impressive results in accelerating pre-trained language models. At the heart of DFKD…

Computation and Language · Computer Science 2022-05-17 Xinyin Ma , Xinchao Wang , Gongfan Fang , Yongliang Shen , Weiming Lu

Decoding by contrasting layers (DoLa), is designed to improve the generation quality of large language models (LLMs) by contrasting the prediction probabilities between an early exit output (amateur logits) and the final output (expert…

Computation and Language · Computer Science 2024-07-16 Wenhao Zhu , Sizhe Liu , Shujian Huang , Shuaijie She , Chris Wendler , Jiajun Chen

Reasoning tasks are crucial in many domains, especially in science and engineering. Although large language models (LLMs) have made progress in reasoning tasks using techniques such as chain-of-thought and least-to-most prompting, these…

Artificial Intelligence · Computer Science 2025-05-06 Sergio Hernández-Gutiérrez , Minttu Alakuijala , Alexander V. Nikitin , Pekka Marttinen

Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-training and argue that existing sequence-level reward-shaping…

Computation and Language · Computer Science 2026-02-24 Yinhan He , Yaochen Zhu , Mingjia Shi , Wendy Zheng , Lin Su , Xiaoqing Wang , Qi Guo , Jundong Li

Semantic Web knowledge representation standards, and in particular RDF and OWL, often come endowed with a formal semantics which is considered to be of fundamental importance for the field. Reasoning, i.e., the drawing of logical inferences…

Machine Learning · Computer Science 2018-11-13 Monireh Ebrahimi , Md Kamruzzaman Sarker , Federico Bianchi , Ning Xie , Derek Doran , Pascal Hitzler

In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, there is no comparably principled basis to justify trust in the content of the text…

Artificial Intelligence · Computer Science 2026-05-15 Leslie G. Valiant

Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generating free-text rationales for their predictions via chain-of-thought (CoT) prompting. While CoT can yield dramatically improved performance,…

Computation and Language · Computer Science 2023-09-01 Peifeng Wang , Zhengyang Wang , Zheng Li , Yifan Gao , Bing Yin , Xiang Ren

There has been recent interest in improving performance of simple models for multiple reasons such as interpretability, robust learning from small data, deployment in memory constrained settings as well as environmental considerations. In…

Machine Learning · Computer Science 2020-06-23 Amit Dhurandhar , Karthikeyan Shanmugam , Ronny Luss

Semantic parsing from denotations faces two key challenges in model training: (1) given only the denotations (e.g., answers), search for good candidate semantic parses, and (2) choose the best model update algorithm. We propose effective…

Computation and Language · Computer Science 2018-09-06 Dipendra Misra , Ming-Wei Chang , Xiaodong He , Wen-tau Yih

To augment language models with the ability to reason, researchers usually prompt or finetune them to produce chain of thought reasoning steps before producing the final answer. However, although people use natural language to reason…

Computation and Language · Computer Science 2023-11-03 Yuntian Deng , Kiran Prasad , Roland Fernandez , Paul Smolensky , Vishrav Chaudhary , Stuart Shieber

In differential equation discovery algorithms, a priori expert knowledge is mainly used implicitly to constrain the form of the expected equation, making it impossible for the algorithm to truly discover equations. Instead, most…

Artificial Intelligence · Computer Science 2025-01-03 Elizaveta Ivanchik , Alexander Hvatov

Chain-of-Thought (CoT) reasoning successfully enhances the reasoning capabilities of Large Language Models (LLMs), yet it incurs substantial computational overhead for inference. Existing CoT compression methods often suffer from a critical…

Machine Learning · Computer Science 2026-05-26 Yuntian Tang , Bohan Jia , Wenxuan Huang , Lianyue Zhang , Jiao Xie , Wenxi Li , Wei Li , Jie Hu , Xinghao Chen Rongrong Ji , Shaohui Lin

Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answer. However, applying extended reasoning to every step…

Artificial Intelligence · Computer Science 2025-10-08 Haiquan Lu , Gongfan Fang , Xinyin Ma , Qi Li , Xinchao Wang