Papers with iterative feedback
Are LLMs Truly Graph-Savvy? A Comprehensive Evaluation of Graph Generation (2025.acl-srw)
Copied to clipboard
| Challenge: | Large language models have demonstrated impressive capabilities across diverse tasks . however, their ability to generate valid graph structures remains underexplored . |
| Approach: | They evaluate large language models on five specialized graph generation tasks . they also test the models using 3 different prompt types: direct, iterative feedback, and program-augmented. |
| Outcome: | The proposed models solve twice as many tasks as general-purpose models, compared to their general-usage peers. |
Compact Language Models with Iterative Text Refinement for Health Dialogue Summarization (2026.eacl-long)
Copied to clipboard
| Challenge: | Health wellness agents typically rely on large language models (LLMs) for response generation, where contextual information from prior conversations can be utilized for response grounding and personalization. |
| Approach: | They propose to use large language models to generate high-quality health dialogue summaries by using iterative feedback. |
| Outcome: | The proposed method outperforms baseline on open-source and proprietary benchmarks and can run on local compute without a GPU. |
Self-Evolving Multi-Agent Systems via Textual Backpropagation (2026.findings-acl)
Copied to clipboard
Xiaowen Ma, Yunpu Ma, Chenyang Lin, Sikuan Yan, Jinhe Bi, Zixuan Cao, Yijun Tian, Volker Tresp, Hinrich Schuetze
| Challenge: | Large Language Models (LLMs) have proven effective for addressing complex, high-dimensional tasks, but current approaches rely on static, manually engineered multi-agent configurations. |
| Approach: | They propose a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. |
| Outcome: | The proposed framework surpasses leading multi-agent baselines under the same configurations, showing consistent performance improvements. |
Enhancing Tool Retrieval with Iterative Feedback from Large Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods have shown that large language models can handle a certain amount of tools through in-context learning or fine-tuning. |
| Approach: | They propose to enhance tool retrieval with iterative feedback from the large language model by prompting the tool usage model to provide feedback for the tool retriever model in multi-round. |
| Outcome: | The proposed approach achieves advanced performance in both in-domain evaluation and out-of-domain assessment. |
Evolving Knowledge Distillation with Large Language Models and Active Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies have focused on the direct use of large language models for text generation and labeling, without fully exploring their potential to comprehend the target task and acquire valuable knowledge. |
| Approach: | They propose to distill the knowledge of large language models into smaller models by generating annotated data. |
| Outcome: | The proposed method improves the performance of small domain models while enhancing the ability of large language models. |
From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Traditional generation methods focus primarily on textual quality, but they fail to meet complex, multifaceted educational requirements. |
| Approach: | They propose a method for automatic generating high-quality mathematical problems that align with educational objectives using a dataset of 16k mathematical questions with multi-dimensional educational objectives. |
| Outcome: | The proposed method improves generating high-quality mathematical questions that meet multi-dimensional educational objectives. |
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. |
Act2P: LLM-Driven Online Dialogue Act Classification for Power Analysis (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on explicit utterance functions, overlooking the implicit power dynamics embedded in dialogue. |
| Approach: | They propose an online Dialogue Act Classification and Dynamic Power Analysis framework based on large language models to integrate dialogue act classification with power quantification. |
| Outcome: | The proposed framework outperforms existing methods in online scenarios and shows that dialogue power is distributed and dynamically transferred. |
KoACD: The First Korean Adolescent Dataset for Cognitive Distortion Analysis via Role-Switching Multi-LLM Negotiation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Cognitive distortions are negative thinking patterns that can lead to mental health issues in adolescents. |
| Approach: | They propose a multi-Large Language Model negotiation method to refine distortion classification . they also use cognitive clarification and cognitive balancing to improve label consistency . |
| Outcome: | The proposed dataset contains 108,717 instances of cognitive distortions in Korean adolescents. |
D2CS - Documents Graph Clustering using LLM supervision (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Document clustering does not inherently ensure thematic consistency. |
| Approach: | They propose a framework that constructs a similarity graph over document embeddings and applies iterative graph-based clustering algorithms to partition the corpus into initial clusters. |
| Outcome: | The proposed framework constructs a similarity graph over document embeddings and applies iterative graph-based clustering algorithms to partition the corpus into initial clusters. |
Let the Comments Speak: A Multi-Agent Framework based on Large Language Model for Comment-Guided Code Refactoring (2026.findings-acl)
Copied to clipboard
| Challenge: | Current Large Language Models focus on syntax and ignore the vital semantic signals in code comments. |
| Approach: | They propose a Multi-Agent framework for COmment-guided code Refactoring that populates original code with precise comments to provide necessary semantic guidance for subsequent refactoring. |
| Outcome: | The proposed framework significantly improves code quality and achieves higher developer acceptance compared to baselines. |