arXiv:2505. 23277v3 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) often suffers from long and noisy retrieved contexts.
The paper introduces INTRA, an attention-based encoder-decoder framework that retrieves directly from its own internal representations instead of using an external retriever. By having decoder attention query pre-encoded evidence chunks, INTRA unifies retrieval and generation, eliminating the typical mismatch seen in retrieval-augmented generation pipelines. Experiments on question-answering benchmarks show that INTRA outperforms strong engineered retrieval pipelines in both evidence recall and overall answer quality.
The paper introduces Retrieval-Augmented Decoding (RAD), a decoding-time method that improves the truthfulness of large language models without retraining. RAD uses a small reference set of up to ten annotated examples to build a grounding space of context embeddings and next-token logits, which it retrieves and aggregates during inference to shape the model’s output. Experiments on four open-ended generation benchmarks and four different LLMs show that RAD consistently outperforms strong baselines and generalizes well across tasks.
arXiv:2606. 06197v1 Announce Type: cross Abstract: Question answering (QA) systems have achieved notable progress with the advent of large language models (LLMs).
arXiv:2609.25537v1 Announce Type: new Abstract: Large language model (LLM) inference is constrained by the quadratic scaling of self-attention and the linear scaling of the KV cache, increasing laten...
arXiv:2606. 06906v1 Announce Type: cross Abstract: Long-context question answering (QA) remains challenging for smaller language models even when answer-bearing evidence is already present in the input.
arXiv:2606. 29844v1 Announce Type: cross Abstract: The quadratic computational cost of traditional attention mechanisms poses a major bottleneck to the scalability and practical deployment of large language models (LLMs), particularly in long-context scenarios.
arXiv:2603. 05353v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) for long-context question answering is bottlenecked by inference-time prefilling over large retrieved contexts.
The paper introduces Highlight-Then-Summarize (H2S), a two-step approach that first highlights question-relevant evidence in long documents and then condenses it into a compact, question-conditioned summary before generating an answer. The authors built the H2S-Dataset with 6,647 examples spanning 11 benchmark families, and developed H2S-RL to reward evidence selection and summary construction. Evaluated on the H2S-Bench suite, the H2S-14B model outperforms larger open-source models, achieving the highest overall score and maintaining strong performance even with a reduced output budget.
arXiv:2609.22100v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves language models with retrieved evidence, but processing many long passages is costly and can introduce...
arXiv:2608.30811v1 Announce Type: cross Abstract: Long-context compression is essential for reducing the cost and latency of large language model inference. However, existing methods can fragment imp...
The paper introduces REVA, a method for compressing retrieval-augmented generation (RAG) prompts by aggregating historical query–document–model interactions into reusable evidence views. REVA mines attention traces from the target generator, maps token-level attention to readable words, aggregates importance across repeated document accesses, and produces budget‑specific plain‑text views that maintain document order and the standard RAG interface. Experiments on four benchmarks with modern LLMs show that REVA improves generation quality by 1.0–5.8 points over existing compressors while reducing compression overhead by 5.3 to 15.6 times and adding less than 40 ms of latency.