Constrained Hybrid Decoding (CHyD) is introduced, a novel faithfulness-first paradigm for speculative RAG that improves exact answer correctness and remains competitive overall, highlighting its suitability for safety-critical information retrieval applications.
This work evaluates Qwen2.5-7B-Instruct under INT8 and INT4 quantization on RGB and HotpotQA, measuring both accuracy and faithfulness with a hallucination detector, NLI entailment, and an LLM judge.
DEX-Comp is proposed, a two-stage training recipe that separates reliable imitation from targeted exploration and applies outcome-based reinforcement learning to teacher-failed questions to directly optimize answer correctness.
This work measures citation attribution across compression methods and budgets, comparing reranking, extractive selection, abstractive summarization, token pruning, and an extract-cluster-rewrite construction on ASQA and QASPER under a fixed generator and primary entailment evaluator.
This work proposes MemSuit, a self-distillation framework in which a teacher summarizer, conditioned on observed query-answer pairs, produces utility-aware memory entries that a student learns to reproduce from the raw conversation alone, confirming the value of grounding memory in downstream utility.
Dynamic vocabularies built on-the-fly via Lempel-Ziv-Welch (LZW) compression let a language model represent the same text in fewer tokens, but prior work shows that this efficiency comes at a cost to reasoning and perplexity. We show that this quality gap is not a fundamental price of compression but can be substantial...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
