Papers with learning framework
Generalization in Generation: A closer look at Exposure Bias (D19-56)
Copied to clipboard
| Challenge: | Autoregressive generative models are often criticized for using ground-truth contexts at training time but generated ones at test time. |
| Approach: | They propose that generalization is the underlying property to address and propose unconditional generation as its fundamental benchmark. |
| Outcome: | The proposed model is generalized and can handle true and generated contexts. |
Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have raised concerns regarding the hallucination and flaws in their reasoning process. |
| Approach: | They propose a framework to learn planning-based reasoning through Direct Preference Optimization on collected trajectories, which are ranked according to synthesized process rewards. |
| Outcome: | The proposed model surpasses GPT-3.5-Turbo on logical reasoning benchmarks on a set of logically-based reasoning tasks. |
Joint Learning from Labeled and Unlabeled Data for Information Retrieval (C18-1)
Copied to clipboard
| Challenge: | Recent studies have focused on neural information retrieval (IR) models. |
| Approach: | They propose a framework which can benefit from both labeled and more abundant unlabeled data . they propose supervised retrieval over several strong baselines for IR . |
| Outcome: | The proposed framework can benefit from labeled and more abundant unlabeled data for representation learning in the context of IR. |
Dialogue Response Selection with Hierarchical Curriculum Learning (2021.acl-long)
Copied to clipboard
Yixuan Su, Deng Cai, Qingyu Zhou, Zibo Lin, Simon Baker, Yunbo Cao, Shuming Shi, Nigel Collier, Yan Wang
| Challenge: | Empirical studies on three benchmark datasets with three state-of-the-art matching models demonstrate that the proposed learning framework significantly improves the model performance across various evaluation metrics. |
| Approach: | They propose a hierarchical curriculum learning framework that trains matching models in an “easy-to-difficult” scheme. |
| Outcome: | The proposed framework significantly improves the model performance across evaluation metrics on three benchmark datasets with three state-of-the-art matching models. |
GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems (2020.emnlp-main)
Copied to clipboard
| Challenge: | End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs. |
| Approach: | They propose a recurrent cell architecture which exploits the structural information in dialogue history . they propose recursive cell architecture to allow representation learning on graphs . |
| Outcome: | The proposed model improves on two different datasets on task-oriented dialogues. |
On the Robustness of Question Rewriting Systems to Questions of Varying Hardness (2022.acl-long)
Copied to clipboard
| Challenge: | entailment : absence of questions classified based on their rewriting hardness or difficulty . enactment of QR system to rewrite context-dependent questions in CQA requires context knowledge . |
| Approach: | They propose a heuristic method to automatically classify questions into subsets of varying hardness . they then conduct a human evaluation to annotate the rewriting hardness of questions . |
| Outcome: | The proposed learning framework improves the overall performance compared to baselines. |
Weakly Supervised Formula Learner for Solving Mathematical Problems (2022.coling-1)
Copied to clipboard
| Challenge: | Existing work suggests a two-phase approach to solving mathematical reasoning tasks . however, its reliance on annotated formulas as intermediate labels throughout its training limited its application. |
| Approach: | They propose a framework that allows models to learn optimal formulas autonomously with weak supervision from the final answers to mathematical problems. |
| Outcome: | The proposed framework outperforms baselines trained on incomplete yet imperfect formula annotations and weakly supervised learning methods on two representative mathematical reasoning datasets. |
Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback (P18-1)
Copied to clipboard
| Challenge: | a recent study shows that counterfactual learning from human bandit feedback can improve neural semantic parsers . cost and difficulty of manually preparing large amounts of parses is a bottleneck for supervised learning . |
| Approach: | They propose to use human bandit feedback to apply counterfactual learning to neural parsing . they devise an easy-to-use interface to collect human feedback on semantic parses . |
| Outcome: | The proposed framework improves semantic parsers by reducing the cost of manual parsing . the proposed framework is based on human bandit feedback collected by the user . |
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained models fail to generalize to unseen data. |
| Approach: | They propose a framework for robust and efficient fine-tuning for pre-trained models . proposed framework achieves new state-of-the-art performance on a number of NLP tasks . |
| Outcome: | The proposed framework outperforms the state-of-the-art T5 model on GLUE, SNLI, SciTail and ANLI. |
Weakly Supervised Semantic Parsing by Learning from Mistakes (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Weakly supervised semantic parsing requires searching consistent logical forms in a huge space and dealing with spurious logical form. |
| Approach: | They propose a learning framework that trains parsers via utterance-denotation pairs . they use utterrance-logical form pairs created from mistakes to bootstrap parser . |
| Outcome: | The proposed framework outperforms state-of-the-art methods on WikiSQL, TabFact and other datasets. |
Be Consistent! Improving Procedural Text Comprehension using Label Consistency (N19-1)
Copied to clipboard
| Challenge: | Existing systems for procedural text comprehension still struggle with this task . evaluative work shows that consistent predictions from multiple entities can improve performance . |
| Approach: | They propose a framework that leverages label consistency during training to improve prediction performance. |
| Outcome: | The proposed framework significantly improves prediction performance over previous state-of-the-art systems on a standard benchmark dataset for procedural text, ProPara. |
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to learn dialogue state tracking and response generation are time-intensive and not transferable between domains. |
| Approach: | They propose a transfer learning framework that allows efficient dialogue state tracking with a minimal generation length. |
| Outcome: | The proposed framework improves the inference efficiency and improves state-of-the-art results on multi-domain multi-tasking systems. |
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to keeping large language models current involve continued pre-training on new documents. |
| Approach: | They propose a learning framework that augments documents with knowledge-intensive tasks created in a self-supervised manner, focusing on memorization, comprehension, and self-reflection. |
| Outcome: | The proposed learning framework improves an LLM’s ability to acquire new knowledge from unseen raw documents through self-teaching. |
Towards Context-Aware Code Comment Generation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for code comments generate comments manually, but they suffer from poor scalability and high maintenance cost due to the expensive overhead of writing comment templates. |
| Approach: | They propose a method to automatically generate code comments at a function level by targeting object-oriented programming languages. |
| Outcome: | The proposed approach outperforms the state-of-the-art methods and is comparable with existing methods. |
MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on knowledge graphs infers a missing relationship between entities with a multi-hop rule . Empirical results show that our multi-chain multi-homing (MCMH) rules yield superior results compared to the standard single-chain approaches. |
| Approach: | They propose to use a generalized form of multi-hop rules to learn generalized rules efficiently . they propose to select a small set of relation chains as a rule and evaluate confidence . |
| Outcome: | The proposed method outperforms the existing methods and the existing frameworks. |
A Logic-Driven Framework for Consistency of Neural Models (D19-1)
Copied to clipboard
| Challenge: | Recent advances in NLP have improved performance on benchmarks such as GLUE . however, tracking performance on a leaderboard is not sufficient to characterize model quality . |
| Approach: | They propose a framework for constraining neural models using logic rules to regularize them away from inconsistency. |
| Outcome: | The proposed framework can be used on natural language inference and is compatible with off-the-shelf learning schemes without model redesign. |
Toward Interpretable Semantic Textual Similarity via Optimal Transport-based Contrastive Sentence Learning (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown that a pretrained language model can capture sentence similarity but there is no interpretation method for the sentence similarities. |
| Approach: | They propose a pretrained language model that captures sentence similarity between embeddings and a transport-based distance measure that leverages semantically-aligned token pairs. |
| Outcome: | The proposed framework outperforms baselines on both STS and interpretable-STS benchmarks and provides interpretation consistent with human judgement. |
FedSpaLLM: Federated Pruning of Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing pruning methods assume public access to calibration data, which is impractical for privacy-sensitive applications. |
| Approach: | They propose a federated learning framework for pruning LLMs that prunes models locally based on private data while accounting for system heterogeneity and communication efficiency. |
| Outcome: | The proposed framework reduces communication overhead and personalizes pruning process based on client resources in federated settings. |
Learning Structured Representations of Entity Names using Active Learning and Weak Supervision (2020.emnlp-main)
Copied to clipboard
| Challenge: | Structured representations of entity names are useful for many entity-related tasks such as entity normalization and variant generation. |
| Approach: | They propose a framework that combines active learning and weak supervision to solve this problem. |
| Outcome: | The proposed framework enables learning of high-quality models from a dozen labeled examples. |
Dual Supervised Learning for Natural Language Understanding and Generation (P19-1)
Copied to clipboard
| Challenge: | Natural language understanding and natural language generation are important research topics in the NLP and dialogue fields. |
| Approach: | They propose a dual-supervised learning framework for natural language understanding and generation on top of dual supervised learning. |
| Outcome: | The proposed framework boosts the performance of both tasks simultaneously in the benchmark experiments. |
An SLA Corpus Annotated with Pedagogically Relevant Grammatical Structures (L18-1)
Copied to clipboard
| Challenge: | a study using a framework to evaluate a language learner's proficiency in a second language aims to examine the production of learners with pedagogically relevant grammatical structures . |
| Approach: | They annotated texts produced by language learners with grammatical structures . they found that learners from different proficiency levels use pedagogically relevant structures compared to those of already certified language learners . |
| Outcome: | The annotated resource SGATe analyzes texts produced by language learners with grammatical structures . structure evolution along levels and level in which they are used the most was studied . |
Polyglot Prompt: Multilingual Multitask Prompt Training (2022.emnlp-main)
Copied to clipboard
| Challenge: | a monolithic framework for multilingual learning can be used without any task/language-specific module. |
| Approach: | They propose a framework to exploit prompting methods for learning a unified semantic space for different languages and tasks with multilingual prompt engineering. |
| Outcome: | The proposed framework can learn tasks from different languages in a monolithic framework without any task/language-specific module. |
Learning New Skills after Deployment: Improving open-domain internet-driven dialogue with human feedback (2023.acl-long)
Copied to clipboard
| Challenge: | Frozen models trained to mimic static datasets can never improve their performance. |
| Approach: | They propose to use binary quality measurements and free-form text feedback to improve conversational skills in a conversational learning framework. |
| Outcome: | The proposed model improves on the DIRECTOR model, which is based on binary quality measurements and free-form text feedback, and shows that iterative retraining and redeployment can improve the model. |
Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Recent time-dependent question answering datasets tend to be biased in either their coverage of time spans or question types. |
| Approach: | They propose a temporal reasoning framework based on temporal span extraction and time-sensitive reinforcement learning to improve the temporal ability of large language models. |
| Outcome: | The proposed framework improves the temporal reasoning capability of large language models by using temporal span extraction and time-sensitive reinforcement learning. |
LOHRec: Leveraging Order and Hierarchy in Generative Sequential Recommendation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | generative recommenders focus on maximizing the prediction probability of the next item in the temporal sequence, ignoring diverse potential items. |
| Approach: | They propose a learning framework that leverages order and hierarchy in generative recommendation using quantized identifiers to further explore performance ceiling of lightweight generative recommenders. |
| Outcome: | The proposed learning framework outperforms strong prior baselines across multiple datasets. |
World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches focus on action selection or use pre-trained models as world models to enhance planning capabilities. |
| Approach: | They propose a new learning framework that optimizes state prediction and action selection through preference learning. |
| Outcome: | The proposed method outperforms existing methods and GPT-4o on VoTa-Bench and Qwen2-VL (7B), LLaVA-1.6 (7B) and LLama-3.2 (11B). |
PLAES: Prompt-generalized and Level-aware Learning Framework for Cross-prompt Automated Essay Scoring (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing cross-prompt automatic essay scoring systems focus on obtaining shared knowledge specific to the target prompt, but this may not be feasible in practical situations because the target essay may not exist as training data. |
| Approach: | They propose a novel learning framework for cross-prompt automatic essay scoring to capture more general knowledge across different prompts and improve the model’s capacity to distinguish between writing levels. |
| Outcome: | The proposed learning framework captures more general knowledge across prompts and improves its capacity to distinguish between writing levels. |
One Planner To Guide Them All ! Learning Adaptive Conversational Planners for Goal-oriented Dialogues (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for goal-oriented dialogues involve training separate models for specific combinations of objectives, leading to computational and scalability issues. |
| Approach: | They propose a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. |
| Outcome: | The proposed method can adapt to varying objective preferences at inference time without retraining. |
Empowering Math Problem Generation and Reasoning for Large Language Model via Synthetic Data based Continual Learning Framework (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing learning frameworks for large language models (LLMs) for math problem generation are limited and lack quality data. |
| Approach: | They propose a synthetic data based continual learning framework to improve LLMs ability for MPG and math reasoning. |
| Outcome: | The proposed framework improves performance on large language models and math reasoning using supervised fine-tuning, data synthesis and direct preference optimization. |
S2H-DPO: Hardness-Aware Preference Optimization for Vision–Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods focus on localized reasoning with pre-specified image indices, bypassing the skills of global visual search and autonomous cross-image comparison. |
| Approach: | They propose a learning framework that constructs multi-image preference data across three hierarchical reasoning levels requiring an increasing level of capabilities. |
| Outcome: | The proposed approach maintains strong single-image reasoning performance while strengthening multi-image understanding capabilities. |