Papers with principled approach
Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs (2026.eacl-short)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) provide strong generative capabilities, but many applications require explicit and fine-grained control over specific textual concepts. |
| Approach: | They propose a framework for fine-grained controllability for single- and dual-concept scenarios . they find performance drops in the dual-constituency setting, even though chosen concepts should be separable . |
| Outcome: | The proposed framework shows that models struggle with compositionality even when concepts are intuitively independent. |
RCScore: Quantifying Response Consistency in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current evaluations of large language models rely on a single instruction template, overlooking models’ sensitivity to instruction style. |
| Approach: | They propose a multi-dimensional framework quantifying how instruction formulation affects model responses by transforming benchmark problems into multiple instruction styles. |
| Outcome: | The proposed framework reveals that instruction style can shift accuracy by 16.7% points. |
NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering (2026.eacl-long)
Copied to clipboard
Kaiwen Shi, Zheyuan Zhang, Zhengqing Yuan, Keerthiram Murugesan, Vincent Galassi, Chuxu Zhang, Yanfang Ye
| Challenge: | Existing methods for nutrition question answering face limited reasoning capacity and contextual overload . poor dietary patterns are associated with more than 11 million deaths in 2017 . |
| Approach: | They propose a framework that enables supervised multi-agent collaboration for nutritional QA. |
| Outcome: | The proposed framework outperforms single-agent and ensemble baselines in multi-agency reasoning tasks. |
Zero-Shot Open-Schema Entity Structure Discovery (2026.eacl-long)
Copied to clipboard
Xueqiang Xu, Jinfeng Xiao, James Barry, Mohab Elkaref, Jiaru Zou, Pengcheng Jiang, Yunyi Zhang, Maxwell J Giammona, Geeth De Mel, Jiawei Han
| Challenge: | Existing methods based on large language models (LLMs) rely heavily on predefined entity attribute schemas or annotated datasets, often leading to incomplete extraction results. |
| Approach: | They propose a novel approach to entity structure extraction that does not require any schema or annotated datasets. |
| Outcome: | Experiments show that ZOES improves LLMs’ ability to extract more complete entity structures across three different domains, showcasing both the effectiveness and generalizability of the method. |
Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic (2023.acl-long)
Copied to clipboard
Connor Pryor, Quan Yuan, Jeremiah Liu, Mehran Kazemi, Deepak Ramachandran, Tania Bedrax-Weiss, Lise Getoor
| Challenge: | Existing DSI approaches infer latent dialog structure without access to domain knowledge. |
| Approach: | They propose a neural-symbolic approach that injects symbolic knowledge into latent space of a generative neural model. |
| Outcome: | The proposed approach boosts performance over the canonical baselines over three dialog structure induction datasets. |
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL (2024.acl-long)
Copied to clipboard
Yunseon Choi, Sangmin Bae, Seonghyun Ban, Minchan Jeong, Chuheng Zhang, Lei Song, Li Zhao, Jiang Bian, Kee-Eung Kim
| Challenge: | Prompt tuning is an important technique for directing model behaviors and eliciting desired responses. |
| Approach: | They propose to find optimal prompt tokens using soft Q-learning to optimize models for prompt tuning. |
| Outcome: | The proposed method improves on baseline prompt tuning, and the results are more natural and interpretable. |
From Confidence to Collapse in LLM Factual Robustness (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation methods focus on performance-based metrics, often investigating from the perspective of prompt perturbations, which captures only the externally triggered side of knowledge robustness. |
| Approach: | They propose a method to measure factual robustness from the perspective of the generation process by analyzing token distribution entropy and temperature scaling sensitivity. |
| Outcome: | The proposed method measures factual robustness from the perspective of the generation process and entropy and temperature scaling sensitivity. |
Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing (2025.acl-long)
Copied to clipboard
| Challenge: | Dynamical systems theory provides a framework for understanding iterative processes and evolution over time. |
| Approach: | They propose to apply this perspective to large language models which iteratively map input text to output text and re-express meaning with linguistic variation. |
| Outcome: | The proposed model reveals that paraphrases re-express meaning with linguistic variation limiting linguistic diversity . |
VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) are used to generate synthetic datasets but lack diversity . prior work has noted that such generated data lacks diversity - a problem that requires domain expertise. |
| Approach: | They propose a principled approach that optimizes a mathematical quantity that optimize the diversity of the dataset using determinantal point processes. |
| Outcome: | The proposed method improves diversity by 1.5-3 times compared to baseline approaches. |
Altogether: Image Captioning via Re-aligning Alt-text (2024.emnlp-main)
Copied to clipboard
Hu Xu, Po-Yao Huang, Xiaoqing Tan, Ching-Feng Yeh, Jacob Kahn, Christine Jou, Gargi Ghosh, Omer Levy, Luke Zettlemoyer, Wen-tau Yih, Shang-Wen Li, Saining Xie, Christoph Feichtenhofer
| Challenge: | Existing captioning models ignore existing alt-text metadata and lack transparency if training data is unknown. |
| Approach: | They propose an approach to edit and re-align alt-texts associated with images using human annotation. |
| Outcome: | The proposed approach improves image captions and improves text-to-image generation and zero-shot image classification tasks. |
Collaborative Rational Speech Act: Pragmatic Reasoning for Multi-Turn Dialog (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing extensions of Rational Speech Act face challenges in scaling to multi-turn, collaborative scenarios. |
| Approach: | They propose a Rational Speech Act extension that optimizes a gain function adapted from rate-distortion theory to model multi-turn dialog by optimizing a model gain . they demonstrate the effectiveness of CRSA on referential games and template-based doctor–patient dialogs in the medical domain. |
| Outcome: | The proposed model yields more consistent, interpretable, and collaborative behavior than baselines, paving the way for more pragmatic and socially aware language agents. |
Visual Text Matters: Improving Text-KVQA with Visual Text Entity Knowledge-aware Large Multimodal Assistant (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge-aware text-based visual question answering methods are based on textual entities in images. |
| Approach: | They propose a visual text entity linking module that harnesses a state-of-the-art visual text recognition engine and the power of a large multimodal model to perform visual text-entity linking. |
| Outcome: | The proposed approach surpasses the previous best approach by 23.3% on an absolute scale and establishes a new state of the art. |
Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for learning from weakly-supervised speech data are hampered by severe data scarcity and the subjective nature of clinical annotations. |
| Approach: | They propose a framework that explicitly models pathological traits by jointly learning from frame-level, segment-level and session-level representations within unsegmented clinical dialogues. |
| Outcome: | The proposed framework is model-agnostic, robust across languages and conditions, and highly data-efficient. |
The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis (2026.acl-long)
Copied to clipboard
Zihao Wei, Liang Pang, Jiahao Liu, Wenjie Shi, Jingcheng Deng, Shicheng Xu, Zenghao Duan, Jingang Wang, Fei Sun, Huawei Shen, Xueqi Cheng
| Challenge: | Explicit reasoning trajectories increase performance but often trigger overthinking . despite its importance, this study examines how each step of reasoning affects the final outcome . |
| Approach: | They propose a Reasoning Completion Point Detector that detects the RCP by monitoring rank dynamics of termination tokens. |
| Outcome: | The proposed method reduces token usage by up to 44% while preserving accuracy. |
GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuning (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing adaptive LoRA methods lack a theoretical foundation to guide this trade-off optimally. |
| Approach: | They propose a principled approach that estimates the intrinsic dimensionality of hidden data representations to adaptively select LoRA ranks. |
| Outcome: | Experiments show that GeLoRA outperforms adaptive LoRA methods by up to +1.0% . |
Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations (2025.emnlp-main)
Copied to clipboard
| Challenge: | Language-driven generative agents have enabled large-scale social simulations with transformative uses, from interpersonal training to aiding global policy-making. |
| Approach: | They propose a framework for persona-environment Behavioral Alignment that iteratively refines agent personas and aligns them with real-world expert benchmarks. |
| Outcome: | The proposed framework greatly enhances behavioral realism and reliability in high-stakes social simulations. |
Interpretability from the Ground Up: Stakeholder-Centric Design of Automated Scoring in Educational Assessments (2026.findings-acl)
Copied to clipboard
| Challenge: | Despite increasing demand for transparency and interpretability, the field has yet to develop a widely accepted solution for interpretable automated scoring to be used in large-scale real-world assessments. |
| Approach: | They propose to develop four principles of interpretability targeted at assessment stakeholder groups to address the need for transparency and interpretability in automated scoring. |
| Outcome: | The proposed framework outperforms many uninterpretable scoring methods in terms of scoring accuracy and is, on average, within 0.06 QWK of the uninterprétable SOTA. |