arXiv AI
Corpus Quality Improves, Retrieval Utility Does Not: An Ablation of Preprocessing and Refinement in a Speech-to-QA Pipeline
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 1
Annotated Surrogate Retrieval for Polish Statutory Law
The paper introduces three retrieval methods for Polish statutory law that use language‑model annotations attached to articles as surrogates. The methods—ASCR, ASCR‑H, and DTF—vary in cost and quality, with ASCR‑H achieving the highest rank‑one accuracy on bar exam questions, while DTF offers competitive performance with lower latency and cost. Extensive evaluation against 14 baselines on 300 exam questions demonstrates significant improvements in head‑rank accuracy and discusses limitations such as coverage asymmetry and negative results for lemmatisation, pseudo‑relevance feedback, and query rewriting.
arXiv Computation and Language
Oct 7
Quality-Aware Self-Correcting Speech Translation on an Edge Device
arXiv:2610.07545v1 Announce Type: new Abstract: We present a fully offline speech-to-speech translation pipeline that runs on a Jetson Nano (4 GB) and corrects its own weak translations without retra...
arXiv Machine Learning
Sep 2
Investigating Linear Probe Robustness to Linguistic Register, Medical Specialty, and Corpus Shifts in Medical QA
arXiv:2609.01361v1 Announce Type: cross Abstract: Linear classifiers trained on hidden states of a large language model (LLM), linear probes, can flag factual errors from a single forward pass. Geome...
arXiv Computation and Language
Oct 5
Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity Spotting
The Writerslogic team participated in the CLEF 2026 SimpleText shared task, tackling both text simplification (Task 1) and complexity spotting (Task 2). For simplification, they built a multi‑candidate pipeline with GPT‑4o‑mini, selecting the best candidate via a reference‑free heuristic, and their Claude Sonnet 4 submission achieved a SARI of 47.43 and BLEU of 14.21, ranking third overall on the Task 1 leaderboard. For complexity spotting, they fine‑tuned a DeBERTa‑v3‑large NLI model on 350 K labeled pairs, achieving a macro F1 of 0.8081 (0.8085 in an ensemble) on binary over‑generation identification and 0.804 accuracy on multi‑class error classification, placing them second among unique teams.
arXiv Computation and Language
3d ago
Retrieval Augmented Generation Compositionality
arXiv:2610.29722v1 Announce Type: new Abstract: Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, rera...
arXiv AI
Sep 25
No More Free Lunch: Corpus Task Complexity Matters as Corpora Grow
The paper introduces Corpus Task Complexity (CTC), a metric that captures how a task’s difficulty scales with corpus size. It distinguishes low‑CTC tasks, whose difficulty grows linearly, from high‑CTC tasks, whose difficulty grows quadratically or more, and presents ten new high‑CTC tasks. Experiments show that models performing well on low‑CTC tasks often fail on high‑CTC tasks, highlighting the need for new approaches to large‑corpus reasoning.