Cross-Encoder Reranking

Patient-specific clinical question answering requires locating the right evidence within long, heterogeneous longitudinal clinical records in which relevant facts may be scattered across encounters, repeated in copied-forward notes, or expressed using different clinical terminology. We evaluated whether biomedical reranking can improve evidence selection and downstream answer quality in a locally deployed retrieval-augmented generation pipeline for longitudinal clinical notes. The pipeline combines PubMedBERT dense retrieval, BM25 lexical retrieval, weighted reciprocal-rank fusion, and MedCPT cross-encoder reranking. Across 1,000 open- and closed-ended question-answer pairs from a cohort of 200 bariatric surgery patients, reranking increased exact source-chunk retrieval within the top 10 items, Hit@10 from 46.6% to 60.6% and mean reciprocal rank from 0.2371 to 0.3252. With Qwen3-8B generation, local judge-assessed answer correctness increased from 44.8% to 48.6%. These results show that biomedical reranking can improve the placement of relevant clinical evidence within a limited context window, although gains in retrieval do not translate proportionally into gains in answer correctness.

Meaning identity (whether two sentences say the same thing after wording changes) is treated in retrieval and RAG as a geometric fact about independently encoded sentence vectors. We show that, for frozen off-the-shelf encoders and language models, it is not: identity is computed when both sentences share one forward pass, and is not a property of the embedding geometry those systems ship. On overlap-matched PAWS-X, purpose-built encoders (BGE, E5, GTE, MiniLM, E5-Mistral-7B) reach English confirm AUC only 0.55-0.65 (dense peak 0.70). Independently encoded last-token states of Llama 3, Mistral, and Qwen do no better; late fusion of the two vectors stays near chance. The same probe on a joint forward pass reaches 0.90-0.96 from 1.5B to 32B, collapses under partner shuffle, is mid-depth, saturates near 0.94 by 3B, and appears more weakly in GPT-2 XL (0.76). The gap holds beyond Llama-style models on other causal LMs, bidirectional encoders (DeBERTa, RoBERTa), and encoder-decoders (Flan-T5, T5, BART). Fixed or linear readers over frozen independent encodings never unlock identity; nonlinear pair readers recover part of it only on the full 49k-pair PAWS train split (0.68-0.87). Off-the-shelf rerankers split: BGE-reranker-large reaches 0.94, while MS-MARCO and Jina stay at 0.55-0.64. Independently trained families compute the same relation and a 1.5B joint reader can distill it from unlabelled teacher scores, while no linear function of the teachers own independent vectors can. Bi-encoders can be fine-tuned to fit PAWS (0.87-0.93), but transfer and STS-B suffer. Cosine compares wording neighbourhoods; identity is a cheap computed operator, not a property of either sentence vector.

Reranking medical procedures against patient queries is a critical component of health insurance information retrieval, complicated by a substantial lexical gap between patient language and clinical nomenclature. We present a systematic comparison of two reranking paradigms for this production task: (1) small cross-encoders (MedCPT, MiniLM-L12) fine-tuned with listwise learning-to-rank objectives across layer freezing configurations, and (2) Qwen3-Reranker-4B, a 4B-parameter instruction reranker whose prompt is iteratively refined via an agentic optimization loop driven by GPT-4.1. On a purpose-built dataset of 2,647 queries across 708 insurance services, we find that a 109M-parameter cross-encoder fine-tuned with ListNet outperforms the 4B-parameter model by 2.6 percentage points on NDCG@3 and 13.3 points on Spearman correlation - at 37x fewer parameters. We report practical findings, a scalable LLM based dataset construction pipeline, and deployment trade-offs relevant to production reranking systems. We release our code and a sample dataset to support reproducibility and adaptation to other domains.

We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19. Rather than proposing a new model, we evaluate a fixed scientific RAG pipeline across three corpus scales: 1,034 chunks (1K papers), 5,160 chunks (5K papers), and 15,480 chunks (15K papers). The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation. Across these settings, hybrid retrieval is more robust than either sparse-only or dense-only retrieval in our setting, reaching Recall@10 of 1.000 at 1K and 15K. In contrast, an MS MARCO-trained cross-encoder reranker reduces precision on the scientific corpus, suggesting that domain mismatch can outweigh the benefits of stronger query-passage interaction. Generation faithfulness measured with RAGAS increases with corpus scale in our setup. Retrieval evaluation uses pseudo-relevance labels derived from the hybrid system, so we treat the results as controlled comparative evidence rather than a benchmark claim. We release code, indexes, and evaluation outputs to support replication and follow-up studies.

Modern reranking recipes---billion-scale cross-encoders, mixture-of-experts (MoE) backbones, and distillation against strong teachers---have outpaced the training infrastructure available to most academic groups. Existing Tevatron reranker training relies on the Hugging Face Trainer with DeepSpeed or PyTorch FSDP1, but these backends lack efficient support for large-scale MoE training. We present Tevatron 3.0, which integrates a Megatron-Core training backend into Tevatron while preserving its data pipeline, evaluation workflow, and Hugging Face-compatible checkpoints. We benchmark existing distributed training configurations against the new backend, showing that Megatron matches FSDP reranker quality and training efficiency under comparable data-parallel settings, is up to 22% faster in the recommended single-node configuration, and supports both LoRA and full-parameter fine-tuning. Crucially, expert parallelism enables training a 30B-parameter Qwen3-30B-A3B MoE reranker, which is infeasible with PyTorch FSDP1. Using this framework, we conduct a controlled comparison of MoE versus dense models, LoRA versus full-parameter tuning, and distillation versus contrastive training on BEIR-15 with three first-stage retrievers, and report serving throughput for Hugging Face and vLLM. We find that the MoE reranker matches dense 8B quality while activating less than half as many parameters and achieving substantially higher inference throughput. We will release the framework and trained checkpoints.

Cross-encoders achieve high reranking accuracy in Retrieval-Augmented Generation (RAG) pipelines but impose quadratic inference costs that limit real-time deployment. We address this by fine-tuning LLaMA 3 (8B) as a drop-in reranker using a two-stage pipeline: supervised fine-tuning on a custom query-document relevance dataset via the Unsloth framework with LoRA adapters, followed by 4-bit quantization for efficient inference. The resulting model replaces the cross-encoder in a dual-retriever RAG pipeline combining BM25 and dense vector search. Evaluated on a domain-specific question-answering benchmark using the RAGAS framework, our fine-tuned LLaMA 3 reranker achieves gains of 14% in answer relevancy, 16% in context precision, 19% in answer similarity, and 21% in answer correctness over the cross-encoder baseline, while reducing inference overhead through 4-bit quantization. These results demonstrate that instruction-tuned LLMs can be adapted into accurate, efficient rerankers without the quadratic complexity of traditional cross-encoders.

Agentic retrieval-augmented generation (RAG) systems combine iterative reasoning loops, query decomposition, and adaptive retrieval to tackle multi-hop question answering. However, the contribution of each component remains poorly understood, particularly under resource-constrained settings using only local language models. Many agentic designs add adaptive retrieval routing and deeper retrieval loops on the assumption that the added complexity helps. To test whether it does, we run a controlled ablation study of a full agentic RAG pipeline evaluated on 5,000 questions from the HotpotQA distractor development set using a local 7B parameter model (Qwen2.5-7B-Instruct). Our full pipeline achieves EM=53.2% and F1=61.6%, compared to a single-pass dense-retrieval baseline of EM=43.1% and F1=54.0%. Across eight ablation conditions, we find that: (1) fixed hybrid retrieval via reciprocal rank fusion consistently outperforms rule-based adaptive routing (+1.8 EM, +1.9 F1), as the routing heuristic over-routes to BM25 by firing on named entities present in nearly all multi-hop sub-questions; (2) two retrieval iterations over the decomposed sub-questions capture 95% of the gains of five, with no meaningful benefit from deeper loops; and (3) query decomposition and cross-encoder reranking each contribute statistically significant but smaller gains (p<0.01 and p<0.001 respectively). Taken together, on a fixed local-model budget, the simpler and fixed choices turn out to be competitive with or better than their adaptive versions: most of the gain comes from running a short retrieval loop, not from adaptive routing or from many iterations. We use no proprietary APIs or large-scale compute.

Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document summarization, graph-based expansion, per-query routing, rank fusion, and corrective re-retrieval. The benefits reported for these methods come almost exclusively from homogeneous corpora, predominantly Wikipedia prose. Whether they hold on the mixed-format collections common in practice, where code, markdown, tables, scientific PDFs, and prose are interleaved within one corpus, has not been measured. To study this directly, we build \textbf{HetDocQA}, a heterogeneous benchmark with \emph{chunker-agnostic} span-overlap relevance labels and collection-disjoint splits, and pair it with MuSiQue and QASPER as homogeneous controls. We evaluate eight methods on a shared backbone, with bootstrap confidence intervals and multiple-comparison correction. A strong cross-encoder reranker accounts for most of the pipeline's quality; beyond it, only two methods yield reliable gains: query expansion and SSCC. SSCC, a per-source calibrated corrector introduced here, sets a separate acceptance threshold for each score source and helps only on heterogeneous data. The remaining reranking and pool-expansion methods in common use, among them hierarchical summarization, graph expansion, routing, and rank fusion, give no reliable gain once that reranker is present.

We describe ConvMemory v2, an opt-in token-evidence reranker that sits after the lightweight ConvMemory v1 reranker and reorders only v1's protected top-10 candidate set. v2 is a fine-tuned ms-marco-MiniLM-L-6-v2 cross-encoder (22,713,601 parameters, measured from the released checkpoint) applied to the ten (query, memory) pairs that v1 has already selected; it does not change which ten memories are returned, so Recall@10 and Hit@10 are identical to v1 by construction, not by statistical coincidence. On the LoCoMo conversational memory benchmark (5 seeds, n = 4955 test rows), v2 raises FULL MRR from v1's 0.5824 to 0.6560 (paired bootstrap +0.0734, 95% CI [+0.0645, +0.0827]) and H@1 from 0.4440 to 0.5474. v2 closes most but not all of the gap to a much more expensive full-pool cross-encoder reference (mxbai-rerank-large-v1 over the top-500, MRR 0.6688): on FULL MRR v2 sits 0.013 below mxbai_top500, but on two raw-dense-hard slices (where v1's protected top-10 has higher recall than mxbai's own top-10) v2 exceeds mxbai_top500. A four-arm load-bearing ablation shows candidate-specific memory text is the mechanism: removing, shuffling, or replacing it collapses MRR below raw dense retrieval. v2 is best understood as a standard recall-preserving cascade pattern with LoCoMo-specific fine-tuning, an explicit anti-shortcut inference contract, and disciplined load-bearing analysis; its advantage over mxbai is slice-specific rather than a general dominance claim. This report extends the v1 technical report (arXiv:2605.28062).

Multi-turn retrieval-augmented generation (RAG) is challenging due to evolving user intent, conversational noise, and strict context limits. We propose a training-free hybrid retrieval pipeline for SemEval-2026 Task 8 that combines dense and sparse retrieval with controlled query rewriting and cross-encoder reranking. On the official test set of Task A, our system achieves 0.5453 nDCG@5, ranking third among 38 teams and outperforming the strongest baseline score of 0.4795. For Task C, we reuse the documents retrieved for Task A and apply a lightweight generation pipeline guided by the official prompt, achieving 0.5312 as the harmonic mean of relevance and faithfulness and ranking 15th among 29 teams. All retrieval components are open-source, while query rewriting and answer generation rely on LLM APIs.

Retrieval-augmented generation systems for legal question answering typically retrieve passages based on semantic similarity and provide them to a language model, which then generates cited answers. Prior work assumes that highly ranked passages are most likely to be usefully cited by the model. Perturbation-based attribution methods, such as C-LIME, have been used exclusively for post-hoc explanation. However, on the AQuAECHR benchmark, semantic similarity does not correlate with passage attribution. Within a retriever's candidate pool, similarity-based ranking performs worse than random selection at surfacing gold citation paragraphs. To address this limitation, a lightweight cross-encoder is trained on continuous perturbation-based attribution scores to re-rank passages prior to generation. This approach is evaluated on the AQuAECHR benchmark, using two language models and five-fold cross-validation. The re-ranker substantially improves citation faithfulness and alignment with gold expert answers. Notably, two re-rankers trained independently on different models converge beyond their raw attribution agreement. This finding indicates that the cross-encoder reduces model-specific noise and produces a shared relevance signal that partially transfers across models, although same-model re-ranking remains more effective. These results demonstrate that perturbation-based attribution provides a practical, model-agnostic training signal for citation-aware retrieval.

We describe ConvMemory, a small 3.6M-parameter learned reranker for conversational long-term memory retrieval, trained with cross-encoder teacher supervision over fused dense and lexical features. On the LongMemEval memory family, ConvMemory operates above the BGE-large cross-encoder in Recall@10 at 12-47x lower latency, remains within 0.025 Recall@10 of mxbai-rerank-large-v1 on Clean500 while running 28x cheaper; under Stress1000 distractors the Recall@10 gap widens to 0.081 but ConvMemory still operates at 117x lower latency; these LongMemEval numbers are single-run or single-seed and are reported as indicative cost-frontier evidence, not benchmark-grade. We then publish a rigorous negative attribution result on a previously claimed mechanism: a five-seed retrained ablation with paired bootstrap shows that ConvMemory's learned temporal window is statistically significant on aggregate but not temporally specific, with the largest effects on hard non-temporal controls and no significant effect on multi-hop temporal queries. The honest description of the mechanism is cheap cross-encoder distillation in a fused dense+lexical feature space, not temporal-structure exploitation. We additionally release CCGE-LA, a low-amplitude conflict-aware candidate-set editor over ConvMemory, as a research preview with modest but consistent gains on supersession and stale/rescue slices on LoCoMo. All results are retrieval-stage; ConvMemory does not match mxbai-rerank-large-v1 in absolute LoCoMo MRR, and the report is single-author and not yet independently audited.

We describe our system for SemEval-2026 Task 8 (MTRAGEval), participating in Task A (Retrieval) across four English-language domains. Our approach employs a three-stage pipeline: (1) query rewriting via a LoRA-fine-tuned Qwen 2.5 7B model that transforms context-dependent follow-up questions into standalone queries, (2) hybrid BM25 and dense retrieval combined through Reciprocal Rank Fusion, and (3) cross-encoder reranking with BGE-reranker-v2-m3. On the official test set, the system achieves nDCG@5 of 0.531, ranking 8th out of 38 participating systems and 10.7% above the organizer baseline. Development comparisons reveal that domain-specific temperature tuning for query generation, where technical domains benefit from deterministic decoding and general domains from controlled randomness, provides consistent gains, while more complex strategies such as domain-aware prompting and multi-query expansion degrade performance.

Retrieval-Augmented Generation (RAG) offers a well-established path to grounding large language model (LLM) outputs in external knowledge, yet the question of which retrieval strategy works best in a high-stakes domain such as biomedicine has not received the controlled, multi-metric treatment it deserves. This paper presents a systematic empirical comparison of five retrieval strategies -- Dense Vector Search, Hybrid BM25 + Dense retrieval, Cross-Encoder Reranking, Multi-Query Expansion, and Maximal Marginal Relevance (MMR) -- within a biomedical question-answering RAG pipeline. All strategies share a fixed generation model (GPT-4o-mini), a common vector store (ChromaDB), and OpenAI's text-embedding-3-small embeddings, ensuring that observed differences are attributable to retrieval alone. Evaluation is conducted on 250 question-answer pairs drawn from a preprocessed subset of the BioASQ benchmark (rag-mini-bioasq) using four DeepEval metrics: contextual precision, contextual recall, faithfulness, and answer relevancy, each reported with 95% confidence intervals. A no-context ablation is included as a lower bound. Cross-Encoder Reranking achieves the best composite score (0.827) and highest contextual precision (0.852), confirming that query-document interaction yields measurable retrieval gains. Multi-Query Expansion, despite its recall-oriented design, produces the weakest contextual precision (0.671), suggesting naive query diversification introduces retrieval noise. MMR sacrifices answer relevancy for diversity, while the Dense baseline (composite 0.822) falls within 0.005 points of the top strategy. All RAG conditions dramatically outperform the no-context ablation on answer relevancy (0.658-0.701 vs. 0.287), confirming the practical value of retrieval. The full pipeline, hyperparameters, and evaluation code are publicly available.