Challenge: Language models (LMs) often struggle to pay enough attention to the input context, and generate texts that are unfaithful or contain hallucinations.
Approach: They propose a context-aware decoding technique that amplifies the difference between the output probabilities when a model is used with and without context.
Outcome: The proposed model significantly improves faithfulness of different LM families including OPT, GPT, LLaMA, and FLAN-T5 for summarization tasks.

Similar Papers

Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model (2024.findings-acl)

Copied to clipboard

Challenge: Large language models lack explicit alignment between source and target contexts, leading to unfaithful translations.
Approach: They propose three learning strategies to encourage LLMs to pay more attention to source context . they use a dataset to test the effectiveness of their model across multiple language pairs .
Outcome: The proposed model reduces hallucinatory translation and improves fidelity across multiple languages.
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods, such as a n-terminal coding, do not provide accurate data for large language models.
Approach: They propose a lightweight framework that leverages attention distributions and uncertainty signals in a single-pass decoding.
Outcome: Experiments on open-book QA datasets show that DAGCD improves faithfulness and robustness while preserving computational efficiency.
Alleviating Hallucinations of Large Language Models through Induced Hallucinations (2025.findings-naacl)

Copied to clipboard

Challenge: Existing studies have shown that large language models generate inaccurate or fabricated information, a phenomenon known as hallucinations.
Approach: They propose a simple strategy to induce-then-contrast decode LLMs to enhance their factuality . they first induce hallucinations from the original model and penalize them .
Outcome: The proposed strategy improves factuality of large language models across task formats, model sizes, and model families.
No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation (2026.findings-acl)

Copied to clipboard

Challenge: Large language models can answer questions and generate summaries when given external contexts.
Approach: They propose a decode-time adapter that backs off to no-context decoding when context is non-informative and uses contrastive fallback under uncertainty.
Outcome: The proposed model prevents neutral regression on baseline-correct items while preserving strong context-driven accuracy on helpful contexts.
C3D: Enhancing LLM Reasoning via Confidence-Guided Contrastive Decoding (2026.findings-acl)

Copied to clipboard

Challenge: Large language models are prone to distraction by contextual information during reasoning tasks.
Approach: They propose a decoding method that uses predicted logits to estimate the model's confidence.
Outcome: The proposed method reveals how the model dynamically activates and adjusts its consideration of each premise as reasoning progresses.
Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps (2024.emnlp-main)

Copied to clipboard

Challenge: Despite the utility and impressive capabilities of large language models, their tendency to generate hallucinations presents a significant challenge in their deployment.
Approach: They propose a simple hallucination detection model based on the ratio of attention weights on the context versus newly generated tokens.
Outcome: The proposed model reduces the amount of hallucinations by 9.6% in a summarization task.
Contrastive Decoding Reduces Hallucinations in Large Multilingual Machine Translation Models (2024.eacl-long)

Copied to clipboard

Challenge: Hallucinations occur when the target side sentence is detached from the source side sentence, or in other words, when there is a low contribution of the source sentence to the generation of the target sentence.
Approach: They propose to use Contrastive Decoding to maximise the log-likelihood difference between a model and the same model with reduced contribution from the encoder outputs.
Outcome: The proposed algorithm maximises the log-likelihood difference between a model and the same model with reduced contribution from the encoder outputs.
Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts (2024.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are easily misled by untruthful contexts provided by users or knowledge augmentation tools, leading to hallucinations.
Approach: They propose a lightweight method to adaptively recognize and mask untruthful context from the inputs and a new evaluation metric to further study the LLMs’ ability to accept truthful information and resist untrusted information.
Outcome: The proposed method can detect and mask untruthful context from the inputs and significantly improve the quality of LLMs’ responses when presented with misleading information.
Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding (2024.naacl-long)

Copied to clipboard

Challenge: Large language models lack contextual knowledge, resulting in text with factual inconsistencies or contextually unfaithful content.
Approach: They propose a method that integrates contrastive decoding with adversarial irrelevant passages as negative samples to enhance robust context grounding during generation.
Outcome: The proposed method improves context grounding during generation without training.
Mitigating Hallucinations in Large Vision-Language Models via Summary-Guided Decoding (2025.findings-naacl)

Copied to clipboard

Challenge: Large Vision-Language Models (LVLMs) generate detailed and coherent responses from visual inputs but are prone to generate hallucinations due to an over-reliance on language priors.
Approach: They propose a method that reduces the text context and controls only the image-related POS tokens to maintain text quality by reducing the text contextualization.
Outcome: The proposed method achieves state-of-the-art performance on object hallucination benchmarks and achieves Pareto optimality among the existing methods.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations