相关论文: Gradient Imitation Reinforcement Learning for Gene…

Internet users have been exposing an increasing amount of Personally Identifiable Information (PII) on social media. Such exposed PII can cause severe losses to the users, and informing users of their PII exposure is crucial to raise their…

Zero-shot cross-lingual information extraction (IE) describes the construction of an IE model for some target language, given existing annotations exclusively in some other language, typically English. While the advance of pretrained…

Graph representation learning (GRL) is a powerful technique for learning low-dimensional vector representation of high-dimensional and often sparse graphs. Most studies explore the structure and metadata associated with the graph using…

Adversarial Imitation Learning (AIL) is a broad family of imitation learning methods designed to mimic expert behaviors from demonstrations. While AIL has shown state-of-the-art performance on imitation learning with only small number of…

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Relation Extraction (RE) aims at recognizing the relation between pairs of entities mentioned in a text. Advances in LLMs have had a tremendous impact on NLP. In this work, we propose a textual data augmentation framework called PGA for…

We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. Except the simple Behavior Cloning (BC)…

While combining imitation learning (IL) and reinforcement learning (RL) is a promising way to address poor sample efficiency in autonomous behavior acquisition, methods that do so typically assume that the requisite behavior demonstrations…

We propose a novel Inverse Reinforcement Learning (IRL) method that mitigates the rigidity of fixed reward structures and the limited flexibility of implicit reward regularization. Building on the Maximum Entropy IRL framework, our approach…

Low-light image enhancement (LLIE) aims to improve low-illumination images. However, existing methods face two challenges: (1) uncertainty in restoration from diverse brightness degradations; (2) loss of texture and color information caused…

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…

Data-driven operations management often relies on parameters estimated from costly human-generated labels. Recent advances in large language models (LLMs) and other AI systems offer inexpensive auxiliary data, but introduce a new challenge:…

Document-level entity-based extraction (EE), aiming at extracting entity-centric information such as entity roles and entity relations, is key to automatic knowledge acquisition from text corpora for various domains. Most document-level EE…

Imitation learning (IL) aims to learn an optimal policy from demonstrations. However, such demonstrations are often imperfect since collecting optimal ones is costly. To effectively learn from imperfect demonstrations, we propose a novel…

In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from instability -- especially as prompt length increases with more…

In weakly-supervised text classification, only label names act as sources of supervision. Predominant approaches to weakly-supervised text classification utilize a two-phase framework, where test samples are first assigned pseudo-labels and…

Pre-ranking is a critical stage in industrial recommendation systems, tasked with efficiently scoring thousands of recalled items for downstream ranking. A key challenge is the train-serving discrepancy: pre-ranking models are trained only…

Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but…

Information retrieval systems increasingly incorporate generative components. For example, in a retrieval augmented generation (RAG) system, a retrieval component might provide a source of ground truth, while a generative component…

In-Context Learning (ICL) has gained prominence due to its ability to perform tasks without requiring extensive training data and its robustness to noisy labels. A typical ICL workflow involves selecting localized examples relevant to a…