Update with illicit numbers

README.md

@@ -28,36 +28,36 @@ Comprehensive evaluation datasets for testing AI model safety mechanisms
 
 | Metric | Value |
 |--------|-------|
-| **Total Conversations** | 979+ |
-| **Total Turns** | 7,706+ |
+| **Total Conversations** | 849+ |
+| **Total Turns** | 6,694+ |
 | **Dataset Types** | 3 complementary methodologies |
-| **Sample Data Available** | 150 conversations |
+| **Sample Data Available** | 15 conversations |
 
 ## 📈 Full Dataset Statistics
 
 | Dataset | Conversations | Turns | Avg Turns/Conv | Focus |
 |---------|--------------|-------|----------------|--------|
-| **Psychology multi-turn** | 207+ | 2,128+ | 10.3 | Psychology harmfulness such as self-harm, psychosis, anthropomorphism, etc. |
-| **Illicit (bioweapon) multi-turn** | 102+ | 1,038+ | 10.2 | Bio-safety harmfulness such as bioweapons, pathogens, etc. |
-| **Illicit (chemical, general) multi-turn** | 670+ | 4,540+ | 6.8 | Non-bio safety harmfulness such as chemical weapons, cyber threats, etc. |
+| **Psychology multi-turn** | 184+ | 1,964+ | 10.3 | Psychology harmfulness such as self-harm, psychosis, anthropomorphism, etc. |
+| **Illicit (bioweapon) multi-turn** | 84+ | 822+ | 9.8 | Bio-safety harmfulness such as bioweapons, pathogens, etc. |
+| **Illicit (chemical, general) multi-turn** | 581+ | 3,908+ | 6.7 | Non-bio safety harmfulness such as chemical weapons, cyber threats, etc. |
 
 ## 🔗 Access Datasets on Hugging Face
 
 ### Psychology Multi-turn Conversations
 Psychology harmfulness such as self-harm, psychosis, anthropomorphism, etc.  
-**Sample:** 50 conversations, 390 turns
+**Sample:** 5 conversations
 
 🔗 **[View Dataset](https://huggingface.co/datasets/GoJulyAI/multi-turn-conversations)**
 
 ### Illicit (bioweapon) Multi-turn Conversations
 Bio-safety harmfulness such as bioweapons, pathogens, etc.  
-**Sample:** 50 conversations, 449 turns
+**Sample:** 5 conversations
 
 🔗 **[View Dataset](https://huggingface.co/datasets/GoJulyAI/multi-turn-bio-transformed-synth-conversations-v1)**
 
 ### Illicit (chemical, general) Multi-turn Conversations
 Non-bio safety harmfulness such as chemical weapons, cyber threats, etc.  
-**Sample:** 50 conversations, 459 turns
+**Sample:** 5 conversations
 
 🔗 **[View Dataset](https://huggingface.co/datasets/GoJulyAI/multi-turn-bio-transformed-synth-conversations-v2)**
 
@@ -83,13 +83,11 @@ All datasets are derived from high-quality, validated conversations with strict
 
 ### Base Criteria
 - Text-based objectives (no code execution templates)
-- NeurIPS evaluation metadata present
 - Verdict: `success` (harmful requests successfully fulfilled)
 - Multi-turn conversations with prompt-response pairs
 
 ### Psychology-Specific Criteria
 - Organic conversations (`organicity = true`)
-- No disclaimer in responses
 - Successfully elicited harmful psychology-related content
 
 ### Illicit-Specific Criteria

index.html

@@ -243,12 +243,12 @@
                 <div class="stats-grid">
                     <div class="stat-card">
                         <h4>Total Conversations</h4>
-                        <div class="number">979+</div>
+                        <div class="number">849+</div>
                         <div class="label">Across all datasets</div>
                     </div>
                     <div class="stat-card">
                         <h4>Total Turns</h4>
-                        <div class="number">7,706+</div>
+                        <div class="number">6694+</div>
                         <div class="label">Multi-turn interactions</div>
                     </div>
                     <div class="stat-card">
@@ -280,23 +280,23 @@
                     <tbody>
                         <tr>
                             <td><strong>Psychology multi-turn</strong></td>
-                            <td>207+</td>
-                            <td>2128+</td>
+                            <td>184+</td>
+                            <td>1964+</td>
                             <td>10.3</td>
                             <td>Psychology harmfulness such as self-harm, psychosis, anthropomorphism, etc.</td>
                         </tr>
                         <tr>
                             <td><strong>Illicit (bioweapon) multi-turn</strong></td>
-                            <td>102+</td>
-                            <td>1038+</td>
-                            <td>10.2</td>
+                            <td>84+</td>
+                            <td>822+</td>
+                            <td>9.8</td>
                             <td>Bio-safety harmfulness such as bioweapons, pathogens, etc.</td>
                         </tr>
                         <tr>
                             <td><strong>Illicit (chemical, general) multi-turn</strong></td>
-                            <td>670+</td>
-                            <td>4540+</td>
-                            <td>6.8</td>
+                            <td>581+</td>
+                            <td>3908+</td>
+                            <td>6.7</td>
                             <td>Non-bio safety harmfulness such as chemical weapons, cyber threats, etc.</td>
                         </tr>
                     </tbody>
@@ -310,19 +310,19 @@
                     <div class="dataset-card">
                         <h4>Psychology Multi-turn Conversations</h4>
                         <p>Psychology harmfulness such as self-harm, psychosis, anthropomorphism, etc.<br>
-                        <strong>Sample:</strong> 50 conversations, 390 turns</p>
+                        <strong>Sample:</strong> 5 conversations</p>
                         <a href="https://huggingface.co/datasets/GoJulyAI/multi-turn-conversations" class="btn" target="_blank">View Dataset →</a>
                     </div>
                     <div class="dataset-card">
                         <h4>Illicit (bioweapon) Multi-turn Conversations</h4>
                         <p>Bio-safety harmfulness such as bioweapons, pathogens, etc.<br>
-                        <strong>Sample:</strong> 50 conversations, 449 turns</p>
+                        <strong>Sample:</strong> 5 conversations</p>
                         <a href="https://huggingface.co/datasets/GoJulyAI/multi-turn-bio-transformed-synth-conversations-v1" class="btn" target="_blank">View Dataset →</a>
                     </div>
                     <div class="dataset-card">
                         <h4>Illicit (chemical, general) Multi-turn Conversations</h4>
                         <p>Non-bio safety harmfulness such as chemical weapons, cyber threats, etc.<br>
-                        <strong>Sample:</strong> 50 conversations, 459 turns</p>
+                        <strong>Sample:</strong> 5 conversations</p>
                         <a href="https://huggingface.co/datasets/GoJulyAI/multi-turn-bio-transformed-synth-conversations-v2" class="btn" target="_blank">View Dataset →</a>
                     </div>
                 </div>
@@ -363,7 +363,6 @@
                 <h3>Base Criteria</h3>
                 <ul>
                     <li>Text-based objectives (no code execution templates)</li>
-                    <li>NeurIPS evaluation metadata present</li>
                     <li>Verdict: <code>success</code> (harmful requests successfully fulfilled)</li>
                     <li>Multi-turn conversations with prompt-response pairs</li>
                 </ul>
@@ -371,7 +370,6 @@
                 <h3>Psychology-Specific Criteria</h3>
                 <ul>
                     <li>Organic conversations (<code>organicity = true</code>)</li>
-                    <li>No disclaimer in responses</li>
                     <li>Successfully elicited harmful psychology-related content</li>
                 </ul>