Agentic Adversarial QA for Improving Domain-Specific LLMs

• URL: http://arxiv.org/abs/2602.18137v1
• Date: Fri, 20 Feb 2026 10:53:09 GMT
• Title: Agentic Adversarial QA for Improving Domain-Specific LLMs
• Authors: Vincent Grari, Ciprian Tomoiaga, Sylvain Lamprier, Tatsunori Hashimoto, Marcin Detyniecki,
• Abstract summary: Large Language Models (LLMs) often struggle to adapt effectively to specialized domains.<n>We propose an adversarial question-generation framework that produces a compact set of semantically challenging questions.
• Score: 53.00642389531106
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs), despite extensive pretraining on broad internet corpora, often struggle to adapt effectively to specialized domains. There is growing interest in fine-tuning these models for such domains; however, progress is constrained by the scarcity and limited coverage of high-quality, task-relevant data. To address this, synthetic data generation methods such as paraphrasing or knowledge extraction are commonly applied. Although these approaches excel at factual recall and conceptual knowledge, they suffer from two critical shortcomings: (i) they provide minimal support for interpretive reasoning capabilities in these specialized domains, and (ii) they often produce synthetic corpora that are excessively large and redundant, resulting in poor sample efficiency. To overcome these gaps, we propose an adversarial question-generation framework that produces a compact set of semantically challenging questions. These questions are constructed by comparing the outputs of the model to be adapted and a robust expert model grounded in reference documents, using an iterative, feedback-driven process designed to reveal and address comprehension gaps. Evaluation on specialized subsets of the LegalBench corpus demonstrates that our method achieves greater accuracy with substantially fewer synthetic samples.

Related papers

• Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis [10.951981109673119]
  Agentic Proposing is a framework that models problem synthesis as a goal-driven sequential decision process.<n>It generates high-precision, verifiable training trajectories across mathematics, coding, and science.<n>A 30B solver trained on only 11,000 synthesized trajectories achieves a state-of-the-art 91.6% accuracy on AIME25.
  arXiv  Detail & Related papers  (2026-02-03T09:02:53Z)
• PL-CA: A Parametric Legal Case Augmentation Framework [10.998168534326709]
  Conventional RAG only injects retrieved documents directly into the model's context.<n>Many existing benchmarks lack expert annotation and focus solely on individual downstream tasks.<n>We propose PL-CA, which introduces a parametric RAG framework to perform data augmentation on corpus knowledge.
  arXiv  Detail & Related papers  (2025-09-08T06:08:06Z)
• Retrieval-augmented reasoning with lean language models [5.615564811138556]
  We develop a retrieval augmented conversational agent capable of interpreting complex, domain-specific queries.<n>Our system integrates a dense retriever with fine-tuned Qwen2.5-Instruct models.<n>All implementation details and code are publicly released to support and adaptation across domains.
  arXiv  Detail & Related papers  (2025-08-15T10:38:15Z)
• Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains [92.36624674516553]
  Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs)<n>We investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education.<n>We utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications.
  arXiv  Detail & Related papers  (2025-03-31T08:22:49Z)
• Synthetic Data Generation Using Large Language Models: Advances in Text and Code [0.0]
  Large language models (LLMs) are transforming synthetic training data generation in both natural language and code domains.<n>We highlight key techniques such as prompt-based generation, retrieval-augmented pipelines, and iterative self-refinement.<n>We discuss the accompanying challenges, including factual inaccuracies in generated text, insufficient stylistic or distributional realism, and risks of bias amplification.
  arXiv  Detail & Related papers  (2025-03-18T08:34:03Z)
• Expert Routing with Synthetic Data for Continual Learning [46.01125098473039]
  Generate to Discriminate (G2D) is a continual learning method that leverages synthetic data to train a domain-discriminator.<n>We observe that G2D outperforms competitive domain-incremental learning methods on tasks in both vision and language modalities.
  arXiv  Detail & Related papers  (2024-12-22T13:16:28Z)
• Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees [3.4289478404209826]
  Large Language Models excel in generative tasks but exhibit inefficiencies in structured text selection.<n>We propose a Learning-to-Defer framework that allocates queries to specialized experts, ensuring high-confidence predictions.
  arXiv  Detail & Related papers  (2024-10-21T08:21:00Z)
• Latent Feature Mining for Predictive Model Enhancement with Large Language Models [2.6334346517416876]
  We introduce an effective approach to formulate latent feature mining as text-to-text propositional logical reasoning. We propose FLAME, a framework that leverages large language models (LLMs) to augment observed features with latent features. We validate our framework with two case studies: the criminal justice system and the healthcare domain.
  arXiv  Detail & Related papers  (2024-10-06T03:51:32Z)
• Exploring Language Model Generalization in Low-Resource Extractive QA [57.14068405860034]
  We investigate Extractive Question Answering (EQA) with Large Language Models (LLMs) under domain drift.<n>We devise a series of experiments to explain the performance gap empirically.
  arXiv  Detail & Related papers  (2024-09-27T05:06:43Z)
• Prompting Encoder Models for Zero-Shot Classification: A Cross-Domain Study in Italian [75.94354349994576]
  This paper explores the feasibility of employing smaller, domain-specific encoder LMs alongside prompting techniques to enhance performance in specialized contexts. Our study concentrates on the Italian bureaucratic and legal language, experimenting with both general-purpose and further pre-trained encoder-only models. The results indicate that while further pre-trained models may show diminished robustness in general knowledge, they exhibit superior adaptability for domain-specific tasks, even in a zero-shot setting.
  arXiv  Detail & Related papers  (2024-07-30T08:50:16Z)
• Optimizing Language Model's Reasoning Abilities with Weak Supervision [48.60598455782159]
  We present textscPuzzleBen, a weakly supervised benchmark that comprises 25,147 complex questions, answers, and human-generated rationales. A unique aspect of our dataset is the inclusion of 10,000 unannotated questions, enabling us to explore utilizing fewer supersized data to boost LLMs' inference capabilities.
  arXiv  Detail & Related papers  (2024-05-07T07:39:15Z)
• Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization [73.89239820192894]
  We argue that automated counterfactual generation should regard several aspects of the produced adversarial instances. We present a novel framework for the generation of counterfactual examples.
  arXiv  Detail & Related papers  (2022-05-20T15:02:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.