Browse AI risks

9 entries

1. 02.02.00 · Risk Category

   Untruthful Content

   "The LLM-generated content could contain inaccurate information"

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 AI Unintentional Post-deployment

2. 02.02.01 · Risk Sub-Category

   Untruthful Content

   Factuality Errors

   "The LLM-generated content could contain inaccurate information" which is factually incorrect

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 AI Unintentional Post-deployment

3. 02.02.02 · Risk Sub-Category

   Untruthful Content

   Faithfulness Errors

   "The LLM-generated content could contain inaccurate information" which is is not true to the source material or input used

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 AI Unintentional Other

4. 02.09.00 · Risk Category

   Hallucinations

   "LLMs generate nonsensical, untruthful, and factual incorrect content"

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 AI Other Post-deployment

5. 02.09.01 · Risk Sub-Category

   Hallucinations

   Knowledge Gaps

   "Since the training corpora of LLMs can not contain all possible world knowledge [114]–[119], and it is challenging for LLMs to grasp the long-tail knowledge within their training data [120], [121], LLMs inherently possess knowledge boundaries [107]. Therefore, the gap between knowledge involved in an input prompt and knowledge embedded in the LLMs can lead to hallucinations"

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 AI Unintentional Other

6. 02.09.02 · Risk Sub-Category

   Hallucinations

   Noisy Training Data

   "Another important source of hallucinations is the noise in training data, which introduces errors in the knowledge stored in model parameters [111]–[113]. Generally, the training data inherently harbors misinformation. When training on large-scale corpora, this issue becomes more serious because it is difficult to eliminate all the noise from the massive pre-training data."

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 AI Unintentional Pre-deployment

7. 02.09.03 · Risk Sub-Category

   Hallucinations

   Defective Decoding Process

   In general, LLMs employ the Transformer architecture [32] and generate content in an autoregressive manner, where the prediction of the next token is conditioned on the previously generated token sequence. Such a scheme could accumulate errors [105]. Besides, during the decoding process, top-p sampling [28] and top-k sampling [27] are widely adopted to enhance the diversity of the generated content. Nevertheless, these sampling strategies can introduce “randomness” [113], [136], thereby increasing the potential of hallucinations"

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 AI Unintentional Pre-deployment

8. 02.09.04 · Risk Sub-Category

   Hallucinations

   False Recall of Memorized Information

   "Although LLMs indeed memorize the queried knowledge, they may fail to recall the corresponding information [122]. That is because LLMs can be confused by co-occurance patterns [123], positional patterns [124], duplicated data [125]–[127] and similar named entities [113]."

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 AI Unintentional Other

9. 02.09.05 · Risk Sub-Category

   Hallucinations

   Pursuing Consistent Context

   "LLMs have been demonstrated to pursue consistent context [129]–[132], which may lead to erroneous generation when the prefixes contain false information. Typical examples include sycophancy [129], [130], false demonstrations-induced hallucinations [113], [133], and snowballing [131]. As LLMs are generally fine-tuned with instruction-following data and user feedback, they tend to reiterate user-provided opinions [129], [130], even though the opinions contain misinformation. Such a sycophantic behavior amplifies the likelihood of generating hallucinations, since the model may prioritize user op

   From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024)

   Domain 3 3.1 Other Unintentional Post-deployment

Informational only, not legal advice. Verify every claim against the linked official sources and consult qualified counsel before acting.