information retrieval engineers

Abstract: Strong multi-hop retrieval should be practical to deploy without expensive corpus preparation or complex database infrastructure. We present SAG2, an embedding-free retrieval architecture built around a single SQLite database, BM25, and contextual evidence decisions from JEV. SAG2 follows the query-time association principle of SAG (SQL-Retrieval Augmented Generation), while replacing its event-entity and dense indexes with a lexical index over original passages. Selected passages supply terms for further retrieval, and newly retrieved evidence guides subsequent decisions. This moves semantic evidence selection to query time, eliminating offline embedding computation, LLM-based event-entity extraction, and dedicated database servers. The resulting system combines lightweight preparation with strong retrieval accuracy: on 1,000-question subsets of MuSiQue, 2WikiMultiHopQA, and HotpotQA, SAG2 achieves the highest Recall@5 and Recall@10 among the compared methods, with Recall@10 of 86.62%, 97.43%, and 99.00%. It also reaches 81.10% document Recall@10 over the 511,962-document EnterpriseRAG-Bench corpus. Indexing all 11,656 MuSiQue passages takes 2.36 seconds, produces a 25.87 MiB database, and requires no model calls. SAG2 demonstrates that accurate multi-hop evidence retrieval can be supported by compact, rapidly prepared infrastructure, making it a practical foundation for knowledge retrieval applications.

Abstract: Open-Web streams can reference real-world events without making them suitable for organization: a correctly linked event may serve only as background, while an event absent from the knowledge base may be central to an item. This distinction reveals an evaluation blind spot in multistage Web systems: pipelines determine not only how inputs are scored, but also which inputs receive scores at all. Using open-Web event admission as a case study, we examine three connected objects (the scored population, the selected operating point, and behavior on the complete input stream) through shared-subset comparisons, admission-loss decomposition, and controlled extraction-recovery interventions. We find that reported ranking differences depend on the scored population, scoring gaps exhibit distinct backbone-dependent failure modes, and recovering missing scores can increase false acceptance under an unchanged threshold. On Original-302, Qwen candidate validity scores 255 of 302 items while direct admission scores all 302; evaluating both on the shared subset narrows their AUC gap. For Mistral, span-safe recovery raises false acceptance from 73.1% to 92.5% with the threshold fixed. Across 602 human-annotated evaluation items within a 3,290-record resource, these findings establish a reporting framework that considers score availability, threshold selection, and complete-stream decisions together.

Abstract: For retrieving prior cases in Indian legal judgments, the problem involves distinguishing relevant legal facts from mere lexical similarities because a prior case that shares a statute with the query judgment is not necessarily relevant. In this paper, we describe an empirical evaluation of three consecutive designs of retrieval systems for the IL PCR(Indian Legal Prior Case Retrieval) task. We demonstrate that the combination of the rhetorical roles (Fact, Ratio Of The Decision, Precedent, Argument, Statute) is better than either using individual roles or performing full text retrieval, that statute similarity is not discriminative, and that a legal entailment reranker with training data produced by an LLM is much worse in terms of official evaluation than its internal validation score. Two rankers, with excellent internal MRR up to 0.97, performed poorly in terms of official evaluation (MRR as low as 0.14). Thus, we propose a new design with query disjoint splitting and frozen validation fusion. The result is a four stage pipeline with Micro F1 0.2549, MRR 0.6081, and nDCG@10 0.4187.

Abstract: Retrieval-Augmented Generation (RAG) is typically evaluated under the implicit assumption that the underlying knowledge base (KB) is clean, leaving the behaviour of RAG systems under realistic KB degradation poorly characterised. We introduce RAGStress, a controlled evaluation benchmark for stress-testing RAG systems under systematic KB corruption. The benchmark pairs four naturalistic corruption types (factual corruption, numeric typo, relevance poisoning, and contradiction injection) with three severity levels (subtle, moderate, and obvious) over a single-KB, metadata-filtered experimental design built from 57 MMLU subjects and 182,546 documents. Across 52,500 model-question-condition evaluations, RAGStress reveals that clean retrieval can mask robustness differences, semantic-fidelity corruptions are substantially more harmful than signal-utility perturbations, no-retrieval accuracy does not predict corrupted-retrieval robustness, and mixed-KB accuracy should not be treated as worst-case robustness. We document the benchmark's intended use, supported claims, and limitations, and provide an artifact bundle including generation scripts, corruption prompts, metadata schema, and evaluation code. RAGStress is intended as a controlled stress test for RAG robustness under KB corruption, not as a general model leaderboard.

Abstract: Efficient vector retrieval requires both a corpus geometry that supports retrieving the right documents through vector similarity, and a query encoder that can embed queries near their desired documents in the embedding space. Recent work has studied geometric capacity through the lens of the minimum embedding dimension needed to realize all top-$k$ answer sets of $n$ documents. We study a different notion of geometric capacity--the maximum recall achievable for a frozen document index--and explore whether learned query encoders can reach this ceiling. On several real-world retrieval benchmarks, we show that retrieval quality of single-vector query encoders often lies far below what the document indices can support. Motivated by this observation, we give theoretical evidence that learning query encoders can be computationally hard. In particular, we construct a retrieval task that (1) admits a query encoder with perfect recall which is representable by a small one-hidden-layer ReLU network, but (2) any statistical-query learner (a class capturing learners that access training data through aggregate statistics) provably requires exponentially many statistical queries to achieve non-trivial recall advantage over the random baseline $k/n$. Taken together, our results suggest substantial unrealized geometric capacity in retrieval benchmarks and establish query encoder learnability as a possible barrier in embedding-based retrieval.

Abstract: Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffected work, or reconstructs a historical task binding. We therefore study \emph{dynamic task routing}, in which an event stream revises task bindings and a system must select the document version valid at each query time before solving it. To study this problem, we repurpose six widely used benchmarks: MMLU, MMLU-Pro, MedMCQA, MATH, GPQA, and HumanEval into 31{,}119 dynamic episodes comprising 373{,}428 temporally categorized queries. This setting exposes a central trade-off: recomputing after every event wastes work, whereas unguarded reuse returns stale conclusions. We introduce the Revision-Aware Independent Agent Graph (RIAG), a bounded multi-agent policy that separates deterministic temporal resolution from task reasoning. RIAG caches solutions by immutable document identity, starts each fresh task with two unexposed attempts, and conditionally invokes audit and repair, using at most four calls per document version. On this collection, homogeneous RIAG achieves 54.24\% joint routing-and-answer accuracy at 0.62 calls/query, compared with 32.22\% at 18.00 calls/query for the strongest comparison method; heterogeneous RIAG reaches 49.78\% at 0.63 calls/query.

Abstract: Retrieval-Augmented Generation has established itself as a fundamental framework in natural language processing, seamlessly integrating information retrieval with the generative capabilities of large language models. However, this process is fundamentally constrained by a critical challenge: semantic space mismatch between queries and retrieved contexts. We propose Knowledge-Aware Semantic Bridging (KASB), a novel framework that improves passage selection quality through semantic space alignment between queries and retrieved documents through intelligent knowledge fusion. Our approach leverages the complementary strengths of generative and retrieval-based knowledge through a multistage process that enhances both relevance and accuracy. We evaluate KASB on three popular open-domain Question Answering datasets to demonstrate the effectiveness of our approach.

Abstract: Open-search fact checking is not merely retrieval followed by classification, but a sequential decision problem in which every query, source visit, and stopping decision reshapes the evidence available for verification. Yet existing systems often distribute these decisions across predefined pipelines or separately prompted modules rather than learning them as a unified task-specific policy. We introduce \textbf{OpenFC}, a unified verification-policy training framework that post-trains Qwen3-8B as a compact next-action controller over reasoning, evidence acquisition, and stopping. OpenFC learns this policy in two stages. \textbf{Stepwise-Calibrated Cold Start (SCCS)} uses a strong training-time supervisor to review post-initial reasoning, tool-use, and stopping proposals before execution, producing reliable trajectories for supervised fine-tuning without access to gold verdicts. \textbf{Verification-Aware Reinforcement Learning (VA-RL)} then improves the cold-start policy on unresolved claims through budget-aware tool rewards, label-aware advantage reweighting, and localized response masking. Across six fact-checking benchmarks, OpenFC achieves 70.39\% average accuracy and 63.30\% macro-F1, the highest overall averages among the evaluated methods. Stage-wise ablations further show that SCCS and VA-RL provide complementary gains, supporting the design of the two-stage training framework. These results position OpenFC as a strong and effective framework for open-search fact-checking. We will open-source our code and release the model checkpoints to support reproducibility.

Abstract: Adaptive RAG often uses retrieval-time signals to decide whether another retrieval, reranking, or multimodal step should run. We ask whether these signals add routing value once the query itself is already known. Across document, audio, and video RAG, we compare matched query-only and query+retrieval routers while holding the optional actions, router family, training procedure, and evaluation fixed. On the held-out final evaluation, adding the tested retrieval signals does not produce a reliable routing improvement over the query-only baseline. Some retrieval signals are associated with whether a later step will help, but that predictability does not consistently lead to bet- ter RUN/SKIP decisions. The main lesson is therefore methodological: retrieval-state features should not be credited with routing value unless they improve over a matched query-only control. Our results do not show that routing or retrieval state is generally useless; they show that the incremental value of retrieval signals must be demonstrated rather than assumed.

Abstract: Topic models summarize large text corpora, but top-ranked words often provide only a limited representation of topic semantics. Sparse autoencoders (SAEs) offer a way to move beyond word-level descriptors by extracting interpretable features from dense representations, yet how feature interpretability relates to topic-inference quality remains unclear. We introduce \textbf{MonoTM}, an interpretable topic modeling framework that decouples these roles. Across three benchmark corpora, we show that document--topic mixture estimation and semantic interpretation favor different SAE configurations and feature subsets. MonoTM estimates mixtures from the full SAE bag-of-features representation and, with them fixed, learns topic descriptors over a separate vocabulary of corpus-grounded semantic features. This design preserves global topic structure while representing topics with semantic units more meaningful than individual words, making them more useful for downstream corpus analysis.

Abstract: Large language models (LLMs) have recently shown promise for historical entity linking, but preference optimization for this task is often formulated with only one negative candidate per training instance. This discards information from the remaining candidates retrieved for the same mention. We introduce multi-negative direct preference optimisation (MDPO), a reference-based pairwise objective that compares the correct entity with all valid rejected candidates associated with each mention. MDPO preserves the Bradley-Terry formulation of DPO while exploiting the complete candidate set through masked, length-normalised sequence scores. We evaluate MDPO on hipe-2020 and newseye, covering French, German, English, Swedish, and Finnish historical newspaper text. Experiments show that MDPO improves over supervised fine-tuning and single-negative DPO, with particularly strong gains for NIL mentions, semantic ambiguity, OCR noise, and historically difficult names. Further analyses disentangle candidate-generation and selection errors, showing that candidate retrieval remains a key bottleneck for end-to-end entity linking. These results demonstrate that incorporating all within-instance negative candidates is a simple and effective improvement for LLM-based historical entity linking.