Copertina

From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Guo, Xiaoyong, Li, Nanjie, Zeng, Zijie, Wang, Kai, Huang, Hao, Xu, Haihua, Shi, Wei
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

Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs
di: Wei, Kangda, et al.
Pubblicazione: (2025)

DepFlow: Disentangled Speech Generation to Mitigate Semantic Bias in Depression Detection
di: Li, Yuxin, et al.
Pubblicazione: (2026)

Steering Towards Fairness: Mitigating Political Bias in LLMs
di: Nadeem, Afrozah, et al.
Pubblicazione: (2025)

From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test
di: Dai, Xunlian, et al.
Pubblicazione: (2025)

FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning
di: Zhang, Zhehao, et al.
Pubblicazione: (2025)

Detecting and Mitigating Bias in LLMs through Knowledge Graph-Augmented Training
di: Kumar, Rajeev, et al.
Pubblicazione: (2025)

Exploring In-Context Learning of Textless Speech Language Model for Speech Classification Tasks
di: Hsu, Ming-Hao, et al.
Pubblicazione: (2023)

Context-Aware Counterfactual Data Augmentation for Gender Bias Mitigation in Language Models
di: Parihar, Shweta, et al.
Pubblicazione: (2026)

InteChar: A Unified Oracle Bone Character List for Ancient Chinese Language Modeling
di: Diao, Xiaolei, et al.
Pubblicazione: (2025)

Benchmarking Contextual and Paralinguistic Reasoning in Speech-LLMs: A Case Study with In-the-Wild Data
di: Wang, Qiongqiong, et al.
Pubblicazione: (2025)

InsideOut: Measuring and Mitigating Insider-Outsider Bias in Interview Script Generation
di: Wan, Yixin, et al.
Pubblicazione: (2025)

MedMT-Bench: Can LLMs Memorize and Understand Long Multi-Turn Conversations in Medical Scenarios?
di: Yang, Lin, et al.
Pubblicazione: (2026)

Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
di: Ranjan, Ravi, et al.
Pubblicazione: (2026)

Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation
di: Chen, Yangneng, et al.
Pubblicazione: (2026)

AGR: Age Group fairness Reward for Bias Mitigation in LLMs
di: Cao, Shuirong, et al.
Pubblicazione: (2024)

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
di: Siddique, Zara, et al.
Pubblicazione: (2025)

Locating and Mitigating Gender Bias in Large Language Models
di: Cai, Yuchen, et al.
Pubblicazione: (2024)

Distance between Relevant Information Pieces Causes Bias in Long-Context LLMs
di: Tian, Runchu, et al.
Pubblicazione: (2024)

Mitigating Bias for Question Answering Models by Tracking Bias Influence
di: Ma, Mingyu Derek, et al.
Pubblicazione: (2023)

Mitigating Context-Memory Conflicts in LLMs through Dynamic Cognitive Reconciliation Decoding
di: Zhou, Yigeng, et al.
Pubblicazione: (2026)

SFR-RAG: Towards Contextually Faithful LLMs
di: Nguyen, Xuan-Phi, et al.
Pubblicazione: (2024)

EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs
di: Zhang, Yuhao, et al.
Pubblicazione: (2025)

Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning
di: Wu, Xuyang, et al.
Pubblicazione: (2025)

Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Context
di: Ruan, Kai, et al.
Pubblicazione: (2024)

GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models
di: Zhang, Tao, et al.
Pubblicazione: (2024)

Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction
di: Li, Guozheng, et al.
Pubblicazione: (2024)

Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles
di: Kim, Jung-hun, et al.
Pubblicazione: (2017)

Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors
di: Li, Guozheng, et al.
Pubblicazione: (2024)

COBIAS: Assessing the Contextual Reliability of Bias Benchmarks for Language Models
di: Govil, Priyanshul, et al.
Pubblicazione: (2024)

Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)
di: Wang, Peidong
Pubblicazione: (2026)

White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs
di: Wan, Yixin, et al.
Pubblicazione: (2024)

DentalBench: Benchmarking and Advancing LLMs Capability for Bilingual Dentistry Understanding
di: Zhu, Hengchuan, et al.
Pubblicazione: (2025)

Mitigating Boundary Ambiguity and Inherent Bias for Text Classification in the Era of Large Language Models
di: Lu, Zhenyi, et al.
Pubblicazione: (2024)

Promoting Equality in Large Language Models: Identifying and Mitigating the Implicit Bias based on Bayesian Theory
di: Deng, Yongxin, et al.
Pubblicazione: (2024)

Capturing Bias Diversity in LLMs
di: Gosavi, Purva Prasad, et al.
Pubblicazione: (2024)

Unveiling the Merits and Defects of LLMs in Automatic Review Generation for Scientific Papers
di: Li, Ruochi, et al.
Pubblicazione: (2025)

Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
di: Wen, Yuchen, et al.
Pubblicazione: (2024)

Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings
di: Xu, Austin, et al.
Pubblicazione: (2025)

UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
di: Zhou, Hanzhang, et al.
Pubblicazione: (2024)

Identifying and Mitigating Social Bias Knowledge in Language Models
di: Chen, Ruizhe, et al.
Pubblicazione: (2024)