Copertina

From Attribution to Abstention: Training-Free Attention-Based Auditing for Clinical Summarization

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yan, Qianqi, Nguyen, Huy, Srivatsa, Sumana, Bandi, Hari, Wang, Xin Eric, Kenthapadi, Krishnaram
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Optimizing Long-Form Clinical Text Generation with Claim-Based Rewards
di: Jhaveri, Samyak, et al.
Pubblicazione: (2025)

RedactOR: An LLM-Powered Framework for Automatic Clinical Data De-Identification
di: Singh, Praphul, et al.
Pubblicazione: (2025)

Balancing Safety and Helpfulness in Healthcare AI Assistants through Iterative Preference Alignment
di: Nghiem, Huy, et al.
Pubblicazione: (2025)

JEDA: Query-Free Clinical Order Search from Ambient Dialogues
di: Singh, Praphul, et al.
Pubblicazione: (2025)

Grounding and Evaluation for Large Language Models: Practical Challenges and Lessons Learned (Survey)
di: Kenthapadi, Krishnaram, et al.
Pubblicazione: (2024)

OG-Rank: Learning to Rank Fast and Slow with Uncertainty and Reward-Trend Guided Adaptive Exploration
di: Singh, Praphul, et al.
Pubblicazione: (2025)

OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs
di: Yan, Qianqi, et al.
Pubblicazione: (2026)

Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
di: Nguyen, Vy, et al.
Pubblicazione: (2025)

ReAttention: Training-Free Infinite Context with Finite Attention Scope
di: Liu, Xiaoran, et al.
Pubblicazione: (2024)

Summarize Before You Speak with ARACH: A Training-Free Inference-Time Plug-In for Enhancing LLMs via Global Attention Reallocation
di: Wang, Jingtao, et al.
Pubblicazione: (2026)

Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
di: Tomani, Christian, et al.
Pubblicazione: (2024)

STRUM-LLM: Attributed and Structured Contrastive Summarization
di: Gunel, Beliz, et al.
Pubblicazione: (2024)

Knowledge Graph Guided Evaluation of Abstention Techniques
di: Vasisht, Kinshuk, et al.
Pubblicazione: (2024)

DAIQ: Auditing Demographic Attribute Inference from Question in LLMs
di: Panda, Srikant, et al.
Pubblicazione: (2025)

Cross-Attention Watermarking of Large Language Models
di: Baldassini, Folco Bertini, et al.
Pubblicazione: (2024)

CompeteSMoE -- Statistically Guaranteed Mixture of Experts Training via Competition
di: Nguyen, Nam V., et al.
Pubblicazione: (2025)

Generating Query-Focused Summarization Datasets from Query-Free Summarization Datasets
di: Chali, Yllias, et al.
Pubblicazione: (2026)

Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Models
di: Yan, Qianqi, et al.
Pubblicazione: (2025)

A Training-Free Length Extrapolation Approach for LLMs: Greedy Attention Logit Interpolation (GALI)
di: Li, Yan, et al.
Pubblicazione: (2025)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
di: Abdaljalil, Samir, et al.
Pubblicazione: (2026)

Adaptive Planning for Multi-Attribute Controllable Summarization with Monte Carlo Tree Search
di: Ryu, Sangwon, et al.
Pubblicazione: (2025)

Permissioned LLMs: Enforcing Access Control in Large Language Models
di: Jayaraman, Bargav, et al.
Pubblicazione: (2025)

Boosting Summarization with Normalizing Flows and Aggressive Training
di: Yang, Yu, et al.
Pubblicazione: (2023)

Hallucination Detection-Guided Preference Optimization for Clinical Summarization
di: Seethakantha, Shamanth Kuthpadi, et al.
Pubblicazione: (2026)

Attribute Structuring Improves LLM-Based Evaluation of Clinical Text Summaries
di: Gero, Zelalem, et al.
Pubblicazione: (2024)

CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
di: Sun, Yuxi, et al.
Pubblicazione: (2025)

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
di: Zong, Haotian, et al.
Pubblicazione: (2026)

Mitigating LLM Hallucinations via Conformal Abstention
di: Yadkori, Yasin Abbasi, et al.
Pubblicazione: (2024)

Multi-Label Clinical Text Eligibility Classification and Summarization System
di: Yerramsetty, Surya Tejaswi, et al.
Pubblicazione: (2025)

Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
di: Jin, Tao, et al.
Pubblicazione: (2026)

Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questions
di: Kirstein, Frederic, et al.
Pubblicazione: (2025)

Attention with Dependency Parsing Augmentation for Fine-Grained Attribution
di: Ding, Qiang, et al.
Pubblicazione: (2024)

Auditable Decision Models with Learned Abstention and Real-Time Steering
di: Chandrasekaran, Sankaranarayanan Palamadai
Pubblicazione: (2026)

A Comparative Study of Quality Evaluation Methods for Text Summarization
di: Nguyen, Huyen, et al.
Pubblicazione: (2024)

Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare
di: Shankar, Ravi, et al.
Pubblicazione: (2025)

Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
di: Liu, Yi, et al.
Pubblicazione: (2025)

Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models
di: Aravindan, Ashwath Vaithinathan, et al.
Pubblicazione: (2026)

Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
di: Zhai, Skylar, et al.
Pubblicazione: (2026)

Training-Free Adaptation of New-Generation LLMs using Legacy Clinical Models
di: Ronaghi, Sasha, et al.
Pubblicazione: (2026)

Jailbreak Detection in Clinical Training LLMs Using Feature-Based Predictive Models
di: Nguyen, Tri, et al.
Pubblicazione: (2025)