Negation is Not Semantic: Diagnosing Dense Retrieval Failure Modes for Trade-offs in Contradiction-Aware Biomedical QA

• URL: http://arxiv.org/abs/2603.17580v1
• Date: Wed, 18 Mar 2026 10:35:44 GMT
• Title: Negation is Not Semantic: Diagnosing Dense Retrieval Failure Modes for Trade-offs in Contradiction-Aware Biomedical QA
• Abstract summary: Large Language Models (LLMs) have demonstrated strong capabilities in question answering, yet their tendency to generate plausible but unverified claims poses serious risks in clinical settings.<n>To mitigate these risks, the TREC 2025 BioGen track mandates grounded answers that explicitly surface contradictory evidence.<n>We present a proxy-based development framework using the SciFact dataset to systematically optimize retrieval architectures.
• Score: 1.0330395403064265
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated strong capabilities in biomedical question answering, yet their tendency to generate plausible but unverified claims poses serious risks in clinical settings. To mitigate these risks, the TREC 2025 BioGen track mandates grounded answers that explicitly surface contradictory evidence (Task A) and the generation of narrative driven, fully attributed responses (Task B). Addressing the absence of target ground truth, we present a proxy-based development framework using the SciFact dataset to systematically optimize retrieval architectures. Our iterative evaluation revealed a "Simplicity Paradox": complex adversarial dense retrieval strategies failed catastrophically at contradiction detection (MRR 0.023) due to Semantic Collapse, where negation signals become indistinguishable in vector space. We further identify a Retrieval Asymmetry: filtering dense embeddings improves contradiction detection but degrades support recall, compromising reliability. We resolve this via a Decoupled Lexical Architecture built on a unified BM25 backbone, balancing semantic support recall (0.810) with precise contradiction surfacing (0.750). This approach achieves the highest Weighted MRR (0.790) on the proxy benchmark while remaining the only viable strategy for scaling to the 30 million document PubMed corpus. For answer generation, we introduce Narrative Aware Reranking and One-Shot In-Context Learning, improving citation coverage from 50% (zero-shot) to 100%. Official TREC results confirm our findings: our system ranks 2nd on Task A contradiction F1 and 3rd out of 50 runs on Task B citation coverage (98.77%), achieving zero citation contradict rate. Our work transforms LLMs from stochastic generators into honest evidence synthesizers, showing that epistemic integrity in biomedical AI requires precision and architectural scalability isolated metric optimization.

Related papers

• Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems [1.7327102304628392]
  Retrieval-Augmented Generation (RAG) grounds Large Language Model (LLM) outputs in external knowledge.<n>We propose an Evaluation Agent that combines Natural Language Inference (NLI) factual verification, a five-signal poison detector with relevance-weighted aggregation, and a Trust Index T = 0.4 F + 0.35 C + 0.25 (1 - P )<n>On TruthfulQA with Llama 3.3 70B, the agent reaches 91% accuracy and 100% precision, with 100% recall on instruction injection.
  arXiv  Detail & Related papers  (2026-08-21T13:42:41Z)
• One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution [85.65263343588026]
  We propose SAGE, a Self-correcting, Autonomous, Grounded Experimenter.<n>Its core mechanism, Multi-Hypothesis Failure Attribution (MHFA), treats recovery as a structured causal diagnosis.<n>On a 12-topic, 5-domain benchmark, SAGE increases metrics-bearing outputs from 42% to 92% over a baseline reflection.
  arXiv  Detail & Related papers  (2026-06-30T10:54:16Z)
• Perception, Verdict, and Evolution: Hindsight-Driven Self-Refining Forensics Agent for AI-Generated Image Detection [80.15317858033534]
  ForeAgent is an agentic forensics framework for AI-generated image detection with iterative self-evolution.<n>ForeAgent achieves state-of-the-art performance on the Chameleon benchmark, reaching 82.18% accuracy.<n>ForeAgent produces more consistent and causally grounded reasoning compared to GPT-5 and GPT-5-mini.
  arXiv  Detail & Related papers  (2026-06-25T02:59:33Z)
• R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search [18.8323743697237]
  Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, fluency does not ensure reliable delivery.<n>We trace this gap to three coupled structural failures: errors propagate without localization, worst-case perturbations go unevaluated, and accumulated knowledge is never invalidated.<n>We argue these share a root cause: abductive, counterfactual, meta-inductive, corrective, and inductive reasoning pull a shared context in incompatible directions.
  arXiv  Detail & Related papers  (2026-06-03T12:45:39Z)
• TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning [60.68349524623048]
  Decompositional jailbreaks pose a critical threat to large language models.<n>We present TwinGate, a stateful dual-encoder defense framework.<n>We construct a comprehensive dataset of over 3.62 million instructions spanning 8,600 distinct malicious intents.
  arXiv  Detail & Related papers  (2026-04-30T13:44:01Z)
• DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection [45.67420390185547]
  We propose PromptFuzz-SC, a semantic-character dual-space mutation framework for evaluating robustness against prompt injection.<n>A hybrid search strategy combining epsilon-greedy exploration and hill-climbing refinement is adopted to efficiently discover high-quality adversarial prompts.<n> Experimental results on DeepSeek demonstrate that dual-space mutation achieves the strongest overall attack performance.
  arXiv  Detail & Related papers  (2026-04-14T10:20:15Z)
• AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing [9.271196825503417]
  Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound.<n>We present AEGIS, a novel multi-agent framework that shifts detection from ungrounded speculation to forensic verification over a closed factual substrate.<n>It reduces the false positive rate by up to 54.40% compared to leading baselines, at an average cost of $0.09 per sample without any task-specific training.
  arXiv  Detail & Related papers  (2026-03-21T04:12:04Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG [65.0203623486525]
  Large Language Models (LLMs) exhibit high reasoning capacity in medical question-answering.<n>Their tendency to produce hallucinations and outdated knowledge poses critical risks in healthcare fields.<n>Existing methods rely on noisy token-level signals and lack the multi-round refinement required for complex reasoning.
  arXiv  Detail & Related papers  (2026-02-06T08:25:30Z)
• A Theoretically Grounded Hybrid Ensemble for Reliable Detection of LLM-Generated Text [0.0]
  We propose a theoretically grounded hybrid ensemble that fuses three complementary detection paradigms.<n>The core novelty lies in an optimized weighted voting framework, where ensemble weights are learned on the probability simplex to maximize F1-score.<n>Our system achieves 94.2% accuracy and an AUC of 0.978, with a 35% relative reduction in false positives on academic text.
  arXiv  Detail & Related papers  (2025-11-27T06:42:56Z)
• DispatchMAS: Fusing taxonomy and artificial intelligence agents for emergency medical services [49.70819009392778]
  Large Language Models (LLMs) and Multi-Agent Systems (MAS) offer opportunities to augment dispatchers.<n>This study aimed to develop and evaluate a taxonomy-grounded, multi-agent system for simulating realistic scenarios.
  arXiv  Detail & Related papers  (2025-10-24T08:01:21Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Deliberative Reasoning Network: An Uncertainty-Driven Paradigm for Belief-Tracked Inference with Pretrained Language Models [7.095344389368656]
  Deliberative Reasoning Network (DRN) is a novel paradigm that reframes logical reasoning from probability to uncertainty minimization.<n>DRN achieves intrinsic interpretability by explicitly tracking belief states and quantifying uncertainty for competing hypotheses.<n>We position DRN as a foundational, verifiable System 2 reasoning component for building more trustworthy AI systems.
  arXiv  Detail & Related papers  (2025-08-06T11:33:35Z)
• Scalable Unit Harmonization in Medical Informatics via Bayesian-Optimized Retrieval and Transformer-Based Re-ranking [0.0]
  We develop a scalable methodology for harmonizing inconsistent units in large-scale clinical datasets.<n>We implement a multi-stage pipeline: filtering, identification, harmonization proposal generation, automated re-ranking, and manual validation.<n>The system achieved 83.39% precision at rank 1 and 94.66% recall at rank 5.
  arXiv  Detail & Related papers  (2025-05-01T19:09:15Z)
• Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization [58.390885294401066]
  Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs)<n>RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions.<n>We propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA)<n>We introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations.
  arXiv  Detail & Related papers  (2025-04-21T04:56:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.