We submit a system description paper for SemEval-2026 Task 8 (MTRAGEval), covering both Subtask A (retrieval) and Subtask B (generation). Our approach is a lightweight, fully reproducible multi-turn RAG pipeline using open-weight models: Qwen2.5-7B-Instruct for query rewriting and grounded answer generation, BGE-M3 for dense retrieval, and BGE-Reranker-v2-M3 for cross-encoder reranking. We report official test performance, conduct ablation experiments to quantify the impact of rewriting and reranking across domains, and provide error analysis using the organizers’ analytics and answerability classes, highlighting key failure modes in multi-turn retrieval specificity and grounded generation.

Gradient conflict between forgetting and retaining objectives is a well-known obstacle in machine unlearning, where opposing gradients on shared parameters cause destructive interference. In Multimodal Large Language Models (MLLMs), cross-modal coupling entangles visual and textual representations within the same parameters, making this conflict considerably more severe. We propose EASE (Efficient Alignment-aware Selective Erasing), which explicitly balances the conflicting gradient directions. EASE first dynamically locates the conflicting parameters at each step by detecting opposite-sign gradients, then performs a manifold-constrained optimization within the two-dimensional subspace spanned by the task gradients to find the linear combination that maximally aligns them, yielding a valid descent direction for both objectives without any manually tuned trade-off coefficient. Nonconflicting parameters keep their standard updates, keeping the method lightweight. Experiments across multiple MLLM architectures and unlearning benchmarks show that EASE achieves superior unlearning efficiency and faster convergence while matching or surpassing existing methods in multimodal quality.

Asymmetric text matching has becoming increasingly indispensable for many downstream tasks (e.g., IR and NLP). Here, asymmetry means that the documents involved for matching hold different amounts of information, e.g., a short query against a relatively longer document. The existing solutions mainly focus on modeling the feature interactions between asymmetric texts, but rarely go one step further to recognize discriminative features and perform feature denoising to enhance relevance learning. In this paper, we propose a novel adaptive feature discrimination and denoising model for asymmetric text matching, called ADDAX. For each asymmetric text pair, ADDAX is devised to explicitly distinguish discriminative features and filter out irrelevant features in a context-aware fashion. Concretely, a matching-adapted gating siamese cell (MAGS) is firstly devised to identify discriminative features and produce the corresponding hybrid representations for a text pair. Afterwards, we introduce a locality-constrained hashing denoiser to perform feature-level denoising by learning a discriminative low-dimensional binary codes for redundantly longer text. Extensive experiments on four real-world datasets from different downstream tasks demostrate that the proposed ADDAX obtains substantial performance gain over 36 up-to-date state-of-the-art alternatives.