Papers with controllability

18 papers
What, When, and How to Ground: Designing User Persona-Aware Conversational Agents for Engaging Dialogue (2023.acl-industry)

Copied to clipboard

Challenge: a personalized dialogue system can generate user-customized responses based on long-term memory about the user's persona.
Approach: They propose a method for building a personalized open-domain dialogue system . they combine weighted dataset blending and negative persona information augmentation methods .
Outcome: The proposed method balances dialogue fluency and tendency to ground while introducing a response-type label to improve controllability and explainability of the grounded responses.
ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to low-rank Adaptation (LoRA) are limited in scalability and controllability.
Approach: They propose a conditional recurrent diffusion framework that generates LoRA parameters directly . they integrate model architecture and textual task specifications to generate task-specific parameters .
Outcome: The proposed framework scales to billions-of-parameter LLMs and maintains controllability.
GRS: Combining Generation and Revision in Unsupervised Sentence Simplification (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods for sentence simplification are supervised or unsupervised . paraphrasing captures complex edit operations, while revision-based methods provide more control and interpretability.
Approach: They propose an unsupervised approach to sentence simplification that combines text generation and text revision.
Outcome: The proposed method improves on the Newsela and ASSET datasets.
Large Language Models with Controllable Working Memory (2023.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have led to a series of breakthroughs in natural language processing due to the massive amounts of world knowledge they memorize during pretraining.
Approach: They propose a method to inject counterfactual and irrelevant contexts into standard supervised datasets to strengthen both controllability and robustness.
Outcome: The proposed method improves controllability and robustness across model architectures and sizes.
Diagnose, Then Repair: A Two-Stage MQM-Guided Post-Editing Framework for Domain-Specific Machine Translation (2026.acl-industry)

Copied to clipboard

Challenge: In practice, LLMs are largely diagnostic, with the signals rarely translating into direct quality improvements under real production constraints.
Approach: They propose a two-stage, evaluator-guided automatic post-editing framework that turns MQM-style evaluation into targeted repairs.
Outcome: The proposed framework improves both COMET and CometKiwi scores over one-stage evaluation methods while severities and error spans show strong agreement with human annotations and human editor preferences.
Control Image Captioning Spatially and Temporally (2021.acl-long)

Copied to clipboard

Challenge: Existing methods to generate image captions with user intention are still under exploration.
Approach: They propose a model that connects Contrastive constraints and Attention Guidance in a loop manner and engages explicit spatial and temporal constraints to the generating process.
Outcome: The proposed model improves performance on a trace-controlled image captioning task.
DiffusEmp: A Diffusion Model-Based Framework with Multi-Grained Control for Empathetic Response Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to generate empathetic responses are monotonous and generic, resulting in shallow empathy and few connections to the context.
Approach: They propose to use explicit control to guide the empathy expression and a framework DiffusEmp to unify the utilization of dialogue context and attribute-oriented control signals.
Outcome: The proposed framework outperforms baselines on EmpatheticDialogue in terms of controllability, informativeness, diversity, and diversity without the loss of context-relatedness.
Detoxifying Language Models Risks Marginalizing Minority Voices (2021.naacl-main)

Copied to clipboard

Challenge: Existing detoxification techniques have been proposed to mitigate toxic LM generations . e.g., detoxification makes LMs more brittle to distribution shift, especially on language used by marginalized groups .
Approach: They propose to use detoxification techniques to reduce toxic LM generations without affecting perplexity or generation quality on nontoxic inputs.
Outcome: The proposed methods hurt equity on language used by marginalized groups, the authors show . they show that detoxification makes LMs more brittle to distribution shift, they say .
Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in large language models have demonstrated impressive language understanding and generation capabilities, enabling them to answer a wide range of questions across various domains.
Approach: They propose a refusal mechanism that instructs LLMs to refuse to answer challenging questions in order to avoid errors.
Outcome: The proposed approach improves the controllability and reliability of large language models and their ability to answer questions across domains.
Controllable Text Generation with Focused Variation (2020.findings-emnlp)

Copied to clipboard

Challenge: Focused-Variation Network (FVN) is a new model to control language generation.
Approach: They propose a model that learns discrete latent spaces for each attribute inside codebooks and uses them to generate fluent text.
Outcome: The proposed model can generate fluent and mostly coherent text on two text generation datasets with annotated content and style, and show state-of-the-art performance as assessed by automatic and human evaluations.
ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control (2025.acl-long)

Copied to clipboard

Challenge: Prior zero-shot TTS models only mimic the speaker’s voice without further control and adjustment capabilities while prior controllable TTS systems cannot perform speaker-specific voice generation.
Approach: They propose a style control module that captures codec representations corresponding to timbre, content, and style in a discrete decoupling codec space.
Outcome: The proposed system can fully clone the speaker's voice and perform speech-specific adjustment and control functions.
Controllable Conversation Generation with Conversation Structures via Diffusion Models (2023.findings-acl)

Copied to clipboard

Challenge: Current generation models fail to effectively utilize rich linguistic and world knowledge to generate coherent long text.
Approach: They propose a conversation generation framework that incorporates human knowledge and conversation structures with both controllability and interpretability for better conversation generation.
Outcome: The proposed framework incorporates human knowledge and conversation structures with both controllability and interpretability for better conversation generation.
Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting (2021.acl-long)

Copied to clipboard

Challenge: Existing QG systems perform substantially worse in answering multi-hop questions than single-hop ones.
Approach: They propose a framework that progressively increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.
Outcome: The proposed framework increases question difficulty through step-by-step rewriting under the guidance of an extracted reasoning chain.
Controllable Open-ended Question Generation with A New Question Type Ontology (2021.acl-long)

Copied to clipboard

Challenge: Existing question types are limited to generating multiple-sense questions . we present a question type-aware question generation framework to generate open-ended questions based on multiple-phrase questions - a task that is less explored .
Approach: They propose a question type-aware question generation framework which predicts question focuses and produces the question.
Outcome: The proposed model improves question quality over competitive comparisons on large-scale datasets.
Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review (2026.acl-long)

Copied to clipboard

Challenge: Existing ARG work lacks author inputs and controls and no evaluation measures response reflection of author signals and effectiveness in addressing reviewer concerns.
Approach: They propose a novel author-in-the-loop framework that integrates domain expertise and author-only information into author response generation (ARG) they also propose re3Align, a large-scale dataset of aligned review–response–revision triplets, where revisions proxy author signals and REspGen, an author- in-the loop ARG framework supporting flexible author input, multi-attribute control, and evaluation-guided refinement.
Outcome: Experiments with SOTA LLMs show that author input and evaluation-guided refinement improves author response quality and controllability–quality trade-offs.
Tag-Instruct: Controlled Instruction Complexity Enhancement through Structure-based Augmentation (2025.findings-acl)

Copied to clipboard

Challenge: High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity.
Approach: They propose a framework that compresses instructions into a compact tag space and enhances complexity through RL-guided tag expansion.
Outcome: The proposed framework outperforms existing methods in the evaluation of instruction complexity augmentation and semantic compression of text into a compact tag space.
ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation (2025.emnlp-main)

Copied to clipboard

Challenge: Controllable Dialogue Generation (CDG) enables chatbots to generate responses tailored to desired attributes like emotion and dialog-act.
Approach: They propose a method which dynamically adjusts the control strength at each generation step according to the model’s entropy in both the language model and attribute classifier probability distributions.
Outcome: The proposed method outperforms existing methods on DailyDialog and MultiWOZ datasets while maintaining fluency and grammar.
MessToClean: Evidence-Grounded Structure-Preserving Reconstruction for Real-World Degraded Exam Paper Images (2026.acl-long)

Copied to clipboard

Challenge: Existing Multimodal Large Language Models (MLLMs) fail under RDEI, leading to disrupted structure and evidence-unsupported hallucinations.
Approach: They propose a backbone-agnostic, evidence-driven pipeline that treats off-the-shelf MLLMs as interchangeable components to improve stem consistency and figure consistency.
Outcome: The proposed pipeline improves stem consistency by 1.01-3.18%, figure consistency by 0.50-49.16%, and refusal F1 by 1.06-10.88% across question types.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations