Hallucinations as Orthogonal Noise: Inference-Time Manifold Alignment via Dynamic Contextual Orthogonalization (2026.findings-acl)
Copied to clipboard
Mingkuan Zhao, Wentao Hu, Tianchen Huang, Yuheng Min, Suquan Chen, Yide Gao, Yanbo Zhai, Shuangyong Song, Xuelong Li
| Challenge: | Hallucinations in Large Language Models persist in critical domains where generated content diverges from contextual facts or logical constraints. |
| Approach: | They propose to generate hallucinations as orthogonal noise relative to the semantic manifold of the residual stream. |
| Outcome: | The proposed method achieves superior contextual faithfulness compared to state-of-the-art methods. |
Similar Papers
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. |
Resonant Context Anchoring: Decoupling Attention Routing and Signal Gain at Inference Time (2026.findings-acl)
Copied to clipboard
Mingkuan Zhao, Yide Gao, Wentao Hu, Suquan Chen, Tianchen Huang, Zhenhua An, Zetao Chang, Xiayu Sun, Yuheng Min
| Challenge: | Existing mitigation strategies rely on suppressing specific neuron activations or employing computationally expensive contrastive decoding mechanisms, which often result in increased perplexity or significantly elevated inference latency. |
| Approach: | They propose a lightweight inference-time intervention method grounded in the perspective of residual stream signal dynamics to resolve the signal attenuation of external evidence during its propagation through deep networks. |
| Outcome: | The proposed method improves contextual faithfulness across multiple factual consistency and strong knowledge-conflict tasks while maintaining the model’s general language understanding capabilities. |
CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing classification-based methods capture noise and spurious correlations while overlooking the underlying causal mechanisms. |
| Approach: | They propose a hallucination detection framework based on structural causal models that captures static and passive signals from internal states and employs counterfactual interventions to disentangle causal reasoning paths from incidental noise. |
| Outcome: | Experiments on four datasets and three widely used LLMs show that the proposed framework improves AUROC and interpretability. |
Why LLMs Hallucinate on Structured Knowledge: A Mechanistic Analysis of Reasoning over Linearized Representations (2026.acl-long)
Copied to clipboard
Shanghao Li, Jinda Han, Yibo Wang, Yuanjie Zhu, Zihe Song, Langzhou He, Kenan Kamel A Alghythee, Philip S. Yu
| Challenge: | Existing literature primarily addresses this problem through external interventions such as retrieval augmentation and prompt engineering at the input or output level. |
| Approach: | They find that LLMs can still produce hallucinated outputs when using structured external knowledge. |
| Outcome: | The proposed models fail to ground the provided knowledge, causing the model to revert to parametric memory. |
Trusting Your Evidence: Hallucinate Less with Context-aware Decoding (2024.naacl-short)
Copied to clipboard
| 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. |
Fine-Grained Detection of Context-Grounded Hallucinations Using LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing representations of hallucinations limit the types of errors that can be expressed, so we propose a new representation based on free-form textual descriptions, capturing the full range of possible errors. |
| Approach: | They propose a benchmark for localizing hallucinations using LLMs with a human annotation of over 1,000 examples and a protocol to verify its quality in a humans evaluation. |
| Outcome: | The proposed representation captures the full range of possible errors, and the best model achieves an F1 score of 0.67. |
Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have shown that LLMs reproduce training artifacts, exploit spurious correlations, and fail when faced with distribution shifts. |
| Approach: | They examine irrelevant context hallucinations in which models integrate misleading contextual cues into their predictions. |
| Outcome: | The proposed model errors are reflected in the model's internal computations, and they are consistent with previous studies. |
Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for reducing hallucinations incur a significant increase in latency. |
| Approach: | They propose a task-agnostic attention-guided head suppression strategy that can be seamlessly integrated during inference without incurring significant compute or latency overhead. |
| Outcome: | The proposed approach reduces hallucinations by 2.7x while maintaining F1 and improves throughput by 1.8% compared to existing methods. |
Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) often generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. |
| Approach: | They propose a method to detect model hallucination by systematic analysis of information flow across model layers. |
| Outcome: | The proposed approach improves model reliability by immediately integrating with universal LLMs without additional training or architectural modifications. |
The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Hallucination in large language models has been studied, but a side effect remains unrecognized . a new study examines the trade-off between truthfulness and safety alignment . |
| Approach: | They propose a method that disentangles hallucination from hallucinian features using sparse autoencoders. |
| Outcome: | The proposed method preserves refusal behavior and task utility while maintaining safety alignment. |