Papers by Adi Simhi
Interpreting Embedding Spaces by Conceptualization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large language models have a significant drawback: they are incomprehensible to humans. |
| Approach: | They propose a method for understanding embeddings by transforming a latent embeddable space into a comprehensible conceptual space. |
| Outcome: | The proposed method compares the semantics of the original latent embedding space to the semantic of the vectors. |
Trust Me, I’m Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work on large language model (LLM) hallucinations associated with model uncertainty or inaccurate knowledge. |
| Approach: | They define and investigate a type of hallucination where a model can answer a question correctly but a perturbation causes it to produce a hallucinous response with high certainty. |
| Outcome: | The proposed mitigations outperform existing methods on CHOKE hallucinations . the findings highlight the need to understand their origins and improve mitigation strategies . |