Rename: prompt-free -> emotion-free (more accurate baseline name)

README.md

@@ -32,7 +32,7 @@ pipeline_tag: text-generation
 
 **EmoDistill turns a 7B base LLM into a domain-adaptive emotion-aware negotiation agent.** It decouples *what emotion to show* (an IQL emotion selector over a 28-emotion vocabulary) from *how to express it* (LoRA-SFT imitation followed by JPO refinement against a per-turn LLM judge) — both learned from a fixed **offline** corpus of LLM-vs-LLM negotiations.
 
-This repository hosts **all eight model variants** from the paper: a full **IQL + LoRA-SFT + JPO** stack and a **prompt-free LoRA-SFT-only baseline**, one of each per benchmark domain — **CRAD**, **DESRD**, **SSAD**, **SSD** — for direct head-to-head comparison.
+This repository hosts **all eight model variants** from the paper: a full **IQL + LoRA-SFT + JPO** stack and an **emotion-free LoRA-SFT-only baseline**, one of each per benchmark domain — **CRAD**, **DESRD**, **SSAD**, **SSD** — for direct head-to-head comparison.
 
 ![EmoDistill workflow](figs/workflow.png)
 
@@ -47,23 +47,23 @@ Every domain comes in two variants:
 | Variant | What it is | Folder pattern |
 |---|---|---|
 | **EmoDistill (full)** — IQL + LoRA-SFT + JPO | The main method: IQL emotion selector picks the emotion, LoRA-SFT adapter expresses it, JPO refines against an LLM judge. Reported as **best** in the paper. | `<domain>/emodistill/` |
-| **Prompt-free baseline** — LoRA-SFT only | LoRA fine-tune on the same offline corpus **without** the IQL emotion controller and **without** the JPO judge loop. Isolates "imitation alone" so you can attribute gains to the emotion control + judge components. | `<domain>/promptfree/` |
+| **Emotion-free baseline** — LoRA-SFT only | LoRA fine-tune on the same offline corpus **without** the IQL emotion controller and **without** the JPO judge loop. Isolates "imitation alone" so you can attribute gains to the emotion control + judge components. | `<domain>/emotionfree/` |
 
 Across the four benchmark domains:
 
-| Domain | Paper acronym | EmoDistill (full) | Prompt-free baseline |
+| Domain | Paper acronym | EmoDistill (full) | Emotion-free baseline |
 |---|---|---|---|
-| Credit / debt recovery | **CRAD** | [`crad/emodistill/`](./crad/emodistill) | [`crad/promptfree/`](./crad/promptfree) |
-| Disaster / emergency response | **DESRD** | [`desrd/emodistill/`](./desrd/emodistill) | [`desrd/promptfree/`](./desrd/promptfree) |
-| Student bedtime negotiation | **SSAD** | [`ssad/emodistill/`](./ssad/emodistill) | [`ssad/promptfree/`](./ssad/promptfree) |
-| Surgical scheduling | **SSD** | [`ssd/emodistill/`](./ssd/emodistill) | [`ssd/promptfree/`](./ssd/promptfree) |
+| Credit / debt recovery | **CRAD** | [`crad/emodistill/`](./crad/emodistill) | [`crad/emotionfree/`](./crad/emotionfree) |
+| Disaster / emergency response | **DESRD** | [`desrd/emodistill/`](./desrd/emodistill) | [`desrd/emotionfree/`](./desrd/emotionfree) |
+| Student bedtime negotiation | **SSAD** | [`ssad/emodistill/`](./ssad/emodistill) | [`ssad/emotionfree/`](./ssad/emotionfree) |
+| Surgical scheduling | **SSD** | [`ssd/emodistill/`](./ssd/emodistill) | [`ssd/emotionfree/`](./ssd/emotionfree) |
 
 Inside each `emodistill/` subfolder:
 - `adapter/` — LoRA-SFT+JPO adapter weights (`adapter_model.safetensors`, `adapter_config.json`)
 - `iql/` — IQL emotion selector weights (`q_net.pt`, `v_net.pt`, `policy.pt`)
 - `config.json` — IQL hyperparameters, emotion vocabulary, JPO settings
 
-Inside each `promptfree/` subfolder:
+Inside each `emotionfree/` subfolder:
 - `adapter/` — LoRA-SFT-only adapter weights
 
 ---
@@ -78,7 +78,7 @@ EmoDistill composes **three offline-trained components** at inference (full vari
 
 All three components are **fully offline** — no live LLM API at training time after the negotiation log is collected — and **edge-deployable**: at inference, the runtime is a single 7B model with a LoRA adapter (a few hundred MB) plus a small Q-network for emotion selection.
 
-The **prompt-free baseline** isolates the contribution of the IQL + JPO components by training only the LoRA-SFT step on the same offline turns, with no emotion conditioning and no judge refinement.
+The **emotion-free baseline** isolates the contribution of the IQL + JPO components by training only the LoRA-SFT step on the same offline turns, with no emotion conditioning and no judge refinement.
 
 ## 🚀 Intended use
 
@@ -98,7 +98,7 @@ Companion baselines (same benchmarks, same protocol — full numbers in the pape
 - **[EmoMAS](https://github.com/Yunbo-max/EmoMAS)** (ACL 2026 Main, top 9%, [arXiv:2604.07003](https://arxiv.org/abs/2604.07003)) — Bayesian multi-agent orchestration, no pre-training.
 - Vanilla 7B (no adapter, no emotion guidance).
 
-**Headline result:** EmoDistill (full) achieves the highest utility across all four domains, surpassing both vanilla and prompt-free baselines, and outperforming the other emotion-aware methods on edge-deployable 7B compute budgets.
+**Headline result:** EmoDistill (full) achieves the highest utility across all four domains, surpassing both vanilla and emotion-free baselines, and outperforming the other emotion-aware methods on edge-deployable 7B compute budgets.
 
 ## 📦 Quick start (after checkpoint release)
 
@@ -111,10 +111,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 base = "Qwen/Qwen2.5-7B-Instruct"
 repo = "humanlong/EmoDistill-7b"
 
-# Pick: ("crad" | "desrd" | "ssad" | "ssd") x ("emodistill" | "promptfree")
+# Pick: ("crad" | "desrd" | "ssad" | "ssd") x ("emodistill" | "emotionfree")
 domain  = "crad"
 variant = "emodistill"          # full IQL + SFT + JPO
-# variant = "promptfree"        # LoRA-SFT-only baseline
+# variant = "emotionfree"        # LoRA-SFT-only baseline
 
 tok = AutoTokenizer.from_pretrained(base)
 model = AutoModelForCausalLM.from_pretrained(base, device_map="auto", torch_dtype="auto")
@@ -159,6 +159,6 @@ Apache 2.0 — matches the base model.
 | [EQ-Negotiator](https://github.com/Yunbo-max/EQ-Negotiator) | NeurIPS 2025 | Personas + HMM + WSLS for SLMs |
 | [EvoEmo](https://github.com/Yunbo-max/EvoEmo) | arXiv preprint | Online evolutionary emotion policies |
 | [EmoMAS](https://github.com/Yunbo-max/EmoMAS) | ACL 2026 (top 9%) | Bayesian multi-agent orchestration + 4 benchmarks |
-| **EmoDistill** *(this repo)* | under review | Offline distillation: **4 domain models + 4 prompt-free baselines** in a 7B SLM |
+| **EmoDistill** *(this repo)* | under review | Offline distillation: **4 domain models + 4 emotion-free baselines** in a 7B SLM |
 
 🌟 All five papers + dataset + model in one place: [HF Collection — Emotion-Aware LLM Negotiation](https://huggingface.co/collections/humanlong/emotion-aware-llm-negotiation-6a25d88adcd0b6d41c9d8c75)

crad/emotionfree/adapter/README.md

@@ -0,0 +1,11 @@
+# CRAD / emotion-free adapter — placeholder
+
+This subfolder will hold the LoRA adapter weights for the **emotion-free baseline** on the **CRAD** benchmark (Credit Recovery Assessment Dataset (debt recovery)) once training completes.
+
+The emotion-free variant is LoRA-SFT-only — no IQL emotion controller, no JPO judge loop — isolating the contribution of emotion control and the judge in the full EmoDistill pipeline.
+
+Files to expect:
+- `adapter_model.safetensors` — LoRA weights
+- `adapter_config.json` — PEFT config
+
+See the top-level [README](../../../README.md) for the full method and loading examples.

desrd/emotionfree/adapter/README.md

@@ -0,0 +1,11 @@
+# DESRD / emotion-free adapter — placeholder
+
+This subfolder will hold the LoRA adapter weights for the **emotion-free baseline** on the **DESRD** benchmark (Disaster Emotional Support & Rescue Dataset (emergency)) once training completes.
+
+The emotion-free variant is LoRA-SFT-only — no IQL emotion controller, no JPO judge loop — isolating the contribution of emotion control and the judge in the full EmoDistill pipeline.
+
+Files to expect:
+- `adapter_model.safetensors` — LoRA weights
+- `adapter_config.json` — PEFT config
+
+See the top-level [README](../../../README.md) for the full method and loading examples.

ssad/emotionfree/adapter/README.md

@@ -0,0 +1,11 @@
+# SSAD / emotion-free adapter — placeholder
+
+This subfolder will hold the LoRA adapter weights for the **emotion-free baseline** on the **SSAD** benchmark (Student Sleep Alerting Dataset (education)) once training completes.
+
+The emotion-free variant is LoRA-SFT-only — no IQL emotion controller, no JPO judge loop — isolating the contribution of emotion control and the judge in the full EmoDistill pipeline.
+
+Files to expect:
+- `adapter_model.safetensors` — LoRA weights
+- `adapter_config.json` — PEFT config
+
+See the top-level [README](../../../README.md) for the full method and loading examples.

ssd/emotionfree/adapter/README.md

@@ -0,0 +1,11 @@
+# SSD / emotion-free adapter — placeholder
+
+This subfolder will hold the LoRA adapter weights for the **emotion-free baseline** on the **SSD** benchmark (Surgical Scheduling Dataset (healthcare)) once training completes.
+
+The emotion-free variant is LoRA-SFT-only — no IQL emotion controller, no JPO judge loop — isolating the contribution of emotion control and the judge in the full EmoDistill pipeline.
+
+Files to expect:
+- `adapter_model.safetensors` — LoRA weights
+- `adapter_config.json` — PEFT config
+
+See the top-level [README](../../../README.md) for the full method and loading examples.