Papers with supervision
LLM-driven Instruction Following: Progresses and Concerns (2023.emnlp-tutorial)
Copied to clipboard
| Challenge: | a tutorial on task instruction is aimed at researchers and practitioners interested in NLP generalization . labeled examples are unlikely to be available in large numbers or do not exist . |
| Approach: | This tutorial will examine the progress of natural language processing (NLP) using labeled examples. authors propose that task instructions act as a novel resource for supervision. |
| Outcome: | This tutorial aims to answer questions about instruction-driven NLP . it focuses on the use of task instructions in a low-shot scenario . |
SUPP.AI: finding evidence for supplement-drug interactions (2020.acl-demos)
Copied to clipboard
Lucy Lu Wang, Oyvind Tafjord, Arman Cohan, Sarthak Jain, Sam Skjonsberg, Carissa Schoenick, Nick Botner, Waleed Ammar
| Challenge: | Dietary supplements are used by a large portion of the population, but information on their pharmacologic interactions is incomplete. |
| Approach: | They propose an application to search evidence sentences extracted from the literature to identify supplement-drug interactions. |
| Outcome: | The proposed model extracts supplement information and identifies interactions using labeled DDI data. |
Policy Gradient as a Proxy for Dynamic Oracles in Constituency Parsing (P18-2)
Copied to clipboard
| Challenge: | Existing models for constituency parsing are transition based, decomposing production of each parse tree into a sequence of action decisions. |
| Approach: | They propose to use a policy gradient method to reduce exposure bias by allowing exploration during training. |
| Outcome: | The proposed method outperforms static oracle likelihood training on four constituency parsers in three languages on four parser-agnostic languages. |
PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating formal verse poetry use existing poems for supervision, which are difficult to obtain for most languages and poetic forms. |
| Approach: | They propose an unsupervised approach to generate formal verse poetry without supervision . they use control codes to describe meter and rhyme scheme constraints, and train a transformer language model . |
| Outcome: | The proposed method generates poems that follow any given meter and rhyme scheme without training . it is comparable to those written by humans and generates comparable quality poems . |
WARM: A Weakly (+Semi) Supervised Math Word Problem Solver (2022.coling-1)
Copied to clipboard
| Challenge: | Existing approaches to solving math word problems require full supervision in the form of intermediate equations. |
| Approach: | They propose a weakly supervised model that requires only the final answer as supervision to solve math word problems. |
| Outcome: | The proposed model achieves accuracy gains of 4.5% and 32% over current weakly-supervised methods on standard Math23K and AllArith datasets. |
Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System (2023.emnlp-main)
Copied to clipboard
| Challenge: | generative models struggle to distinguish subtle differences among retrieved knowledge records, resulting in suboptimal quality of generated responses. |
| Approach: | They propose to use maximum marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision. |
| Outcome: | The proposed approach improves on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models. |
Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree (D19-1)
Copied to clipboard
| Challenge: | Existing methods to identify sentiment polarity of opinion words are cumbersome due to the amount of opinionated material on the internet. |
| Approach: | They propose a method to identify sentiment polarity of opinion words on a specific aspect of a sentence using neural networks. |
| Outcome: | The proposed method is the state-of-the-art in aspect-based sentiment classification. |
MEGClass: Extremely Weakly Supervised Text Classification via Mutually-Enhancing Text Granularities (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for text classification use human annotations or a set of class seed words for supervision, which can be costly, especially in emerging domains. |
| Approach: | They propose a weakly-supervised method that leverages mutually-enhancing text granularities to learn a contextualized document representation that captures the most discriminative class indicators. |
| Outcome: | Extensive experiments on seven benchmark datasets show that MEGClass outperforms other weakly and extremely weakly supervised methods. |
DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can replicate insecure patterns from training data. |
| Approach: | They propose a framework that leverages distributed security-relevant cues by aggregating representations from multiple upper layers via an attention-based module. |
| Outcome: | Experiments show that the framework improves the secure-and-correct generation rate by 11.9% over baselines. |
ProMed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLMs (2026.acl-long)
Copied to clipboard
Hongxin Ding, Baixiang Huang, Yue Fang, Weibin Liao, Xinke Jiang, Jinyang Zhang, Yinghao Zhu, Zheng Li, Liantao Ma, Junfeng Zhao, Yasha Wang
| Challenge: | Existing medical Large Language Models (LLMs) follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient details. |
| Approach: | They propose a reinforcement learning framework that transitions LLMs toward a proactive paradigm, enabling them to ask clinically valuable questions before decision-making. |
| Outcome: | Experiments on partial-information medical benchmarks show that ProMed outperforms state-of-the-art methods by 6.29% on average and delivers a 54.45% gain over the reactive paradigm. |