English
Related papers

Related papers: Refining neural network predictions using backgrou…

200 papers

Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but…

Machine Learning · Computer Science 2020-08-14 Jooyoung Moon , Jihyo Kim , Younghak Shin , Sangheum Hwang

Protein function annotation is an important yet challenging task in biology. Recent deep learning advancements show significant potential for accurate function prediction by learning from protein sequences and structures. Nevertheless,…

Biomolecules · Quantitative Biology 2024-02-14 Zuobai Zhang , Jiarui Lu , Vijil Chenthamarakshan , Aurélie Lozano , Payel Das , Jian Tang

Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance of LLMs. Underspecified preferences could obscure directions…

Computation and Language · Computer Science 2024-03-22 Kyungjae Lee , Dasol Hwang , Sunghyun Park , Youngsoo Jang , Moontae Lee

Scientists form hypotheses and experimentally test them. If a hypothesis fails (is refuted), scientists try to explain the failure to eliminate other hypotheses. The more precise the failure analysis the more hypotheses can be eliminated.…

Artificial Intelligence · Computer Science 2023-05-25 Rolf Morel , Andrew Cropper

Large language models have demonstrated impressive reasoning capabilities but are inherently limited by their knowledge reservoir. Retrieval-augmented reasoning mitigates this limitation by allowing LLMs to query external resources, but…

Computation and Language · Computer Science 2025-09-22 Yaorui Shi , Sihang Li , Chang Wu , Zhiyuan Liu , Junfeng Fang , Hengxing Cai , An Zhang , Xiang Wang

The fine-tuning of pre-trained language models has a great success in many NLP fields. Yet, it is strikingly vulnerable to adversarial examples, e.g., word substitution attacks using only synonyms can easily fool a BERT-based sentiment…

Computation and Language · Computer Science 2021-12-23 Xinhsuai Dong , Luu Anh Tuan , Min Lin , Shuicheng Yan , Hanwang Zhang

Reinforcement learning (RL) has demonstrated strong potential in training large language models (LLMs) capable of complex reasoning for real-world problem solving. More recently, RL has been leveraged to create sophisticated LLM-based…

Computation and Language · Computer Science 2025-05-22 Bowen Jin , Jinsung Yoon , Priyanka Kargupta , Sercan O. Arik , Jiawei Han

Personalized recommendation requires models that capture sequential user preferences while remaining robust to sparse feedback and semantic ambiguity. Recent work has explored large language models (LLMs) as recommenders and re-rankers, but…

Information Retrieval · Computer Science 2026-04-22 Siqi Liang , Xiawei Wang , Yudi Zhang , Jiaying Zhou

A major challenge in inductive logic programming (ILP) is learning large programs. We argue that a key limitation of existing systems is that they use entailment to guide the hypothesis search. This approach is limited because entailment is…

Artificial Intelligence · Computer Science 2020-04-23 Andrew Cropper , Sebastijan Dumančić

Partial label learning (PLL) is a typical weakly supervised learning, where each sample is associated with a set of candidate labels. Its basic assumption is that the ground-truth label must be in the candidate set, but this assumption may…

Computer Vision and Pattern Recognition · Computer Science 2025-10-09 Zheng Lian , Mingyu Xu , Lan Chen , Licai Sun , Bin Liu , Lei Feng , Jianhua Tao

When language models (LMs) are trained via reinforcement learning (RL) to generate natural language "reasoning chains", their performance improves on a variety of difficult question answering tasks. Today, almost all successful applications…

Machine Learning · Computer Science 2026-05-18 Mehul Damani , Isha Puri , Stewart Slocum , Idan Shenfeld , Leshem Choshen , Yoon Kim , Jacob Andreas

We introduce iterative retrieval, a novel framework that empowers retrievers to make iterative decisions through policy optimization. Finding an optimal portfolio of retrieved items is a combinatorial optimization problem, generally…

Computation and Language · Computer Science 2024-06-24 Yunmo Chen , Tongfei Chen , Harsh Jhamtani , Patrick Xia , Richard Shin , Jason Eisner , Benjamin Van Durme

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

Machine Learning · Computer Science 2025-01-15 Yaowen Ye , Cassidy Laidlaw , Jacob Steinhardt

In this paper we examine the limitations of Large Language Models (LLMs) for complex reasoning tasks. Although recent works have started to employ formal languages as an intermediate representation for reasoning tasks, they often face…

Logic in Computer Science · Computer Science 2024-08-07 Shashank Kirtania , Priyanshu Gupta , Arjun Radhakirshna

Constraints are essential for stabilizing reinforcement learning fine-tuning (RFT) and preventing degenerate outputs, yet they inherently conflict with the optimization objective because stronger constraints limit the ability of a…

Machine Learning · Computer Science 2026-03-20 Hao Ma , Zhiqiang Pu , Yang Liu , Xiaolin Ai

While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where models gain training rewards but lose generalization. Our…

Artificial Intelligence · Computer Science 2025-11-07 Zeng Zhiyuan , Jiashuo Liu , Zhangyue Yin , Ge Zhang , Wenhao Huang , Xipeng Qiu

Reinforcement learning is used to align language models with human preference signals after first pre-training the model to predict the next token of text within a large corpus using likelihood maximization. Before being deployed in a…

Computation and Language · Computer Science 2024-08-30 Alec Solway

Recent studies strive to incorporate various human rationales into neural networks to improve model performance, but few pay attention to the quality of the rationales. Most existing methods distribute their models' focus to…

Computation and Language · Computer Science 2021-06-04 Quzhe Huang , Shengqi Zhu , Yansong Feng , Dongyan Zhao

Transformer networks, particularly those achieving performance comparable to GPT models, are well known for their robust feature extraction abilities. However, the nature of these extracted features and their alignment with human-engineered…

Information Retrieval · Computer Science 2025-07-23 Tanya Chowdhury , Atharva Nijasure , James Allan

Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text…

Computation and Language · Computer Science 2021-01-13 Evgeny Lagutin , Daniil Gavrilov , Pavel Kalaidin