conftrace_

decoding strategy

60 papers

Explore in graph

Co-occurring keywords

text generation (2913) large language model (13587) language model (4599) hallucination mitigation (320) beam search (309) neural machine translation (2310) nucleus sampling (26) text diversity (18) dialogue generation (454) factual accuracy (108)

Papers

Language Drift in Multilingual Retrieval-Augmented Generation: Characterization and Decoding-Time Mitigation AAAI 2026
Empirical Analysis of Decoding Biases in Masked Diffusion Models ACL 2026
Confidence Should Be Calibrated More Than One Turn Deep ACL 2026
VCGD: Visual Clue Guided Decoding with Caption Model for Mitigating Hallucination in Multimodal Large Language Models AAAI 2026
Anchoring the Cache: Mitigating Contextual Hallucination in KV-Compressed Long-Context Summarization ACL 2026
Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics ACL 2026
Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models EMNLP 2025
The Law of Knowledge Overshadowing: Towards Understanding, Predicting and Preventing LLM Hallucination ACL 2025
Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Models EMNLP 2025
Uncertainty-Aware Contrastive Decoding ACL 2025
Make Good Use of GujiRoBERTa to Identify Entities in Ancient Chinese NAACL 2025
DSVD: Dynamic Self-Verify Decoding for Faithful Generation in Large Language Models EMNLP 2025
DeLTa: A Decoding Strategy based on Logit Trajectory Prediction Improves Factuality and Reasoning Ability EMNLP 2025
The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination ACL 2025
CoCoLex: Confidence-guided Copy-based Decoding for Grounded Legal Text Generation ACL 2025
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation EMNLP 2025
Genre Matters: How Text Types Interact with Decoding Strategies and Lexical Predictors in Shaping Reading Behavior EMNLP 2025
How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Study EMNLP 2025
Probing LLM World Models: Enhancing Guesstimation with Wisdom of Crowds Decoding EMNLP 2025
ECO Decoding: Entropy-Based Control for Controllability and Fluency in Controllable Dialogue Generation EMNLP 2025
Avoidance Decoding for Diverse Multi-Branch Story Generation EMNLP 2025
Dynamic Evil Score-Guided Decoding: An Efficient Decoding Framework For Red-Team Model ACL 2025
Mimicking How Humans Interpret Out-of-Context Sentences Through Controlled Toxicity Decoding NAACL 2025
G2: Guided Generation for Enhanced Output Diversity in LLMs EMNLP 2025
Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts ACL 2025