qwen3-1.7b-context-adherence-guardrail

Qwen3-1.7B — Context-Adherence Guardrail (QLoRA)

A 1.7B realtime guardrail that decides whether a RAG answer is grounded in its retrieved context. It emits a single token — PASS or FAIL — so the verdict costs one forward pass and its logprob doubles as a confidence score.

Behavior Spec

Given a question, retrieved context, and a candidate response, emit FAIL iff the response makes at least one factual claim that is unsupported by or contradicts the retrieved context — truth in the real world is irrelevant (strict grounding); PASS otherwise, including responses that explicitly decline to answer for lack of context.

Judged at response level. Unsupported-but-true world knowledge is FAIL. Abstention is PASS.

Results

Full held-out set: 8,295 human-annotated items (RAGTruth test + FaithBench + HaluBench with the HaluEval subset excised). No LLM judged these — the labels are human.

Spec adherence = pooled balanced accuracy. Robustness = worst per-set balanced accuracy.

Against frontier models, same 60 hard scenarios

Scenarios are disagreement-mined: FaithBench ships 8 detector scores per item, ranked by variance across them (selected items ~2x the corpus median disagreement).

n=60, so a 95% interval is roughly +/-0.12. The honest claim is parity-region, not victory.

The error profiles are opposites. Prompted frontier judges run high recall / low specificity — they catch hallucinations and also reject grounded answers. This model inverts it: specificity 0.833, recall 0.533. For a guardrail gating production traffic, false alarms are the expensive error, which favours this profile — but see Limitations.

Usage

The prompt must be rendered exactly as in training or the numbers do not transfer.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

BASE = "Qwen/Qwen3-1.7B"
tok = AutoTokenizer.from_pretrained(BASE)
model = PeftModel.from_pretrained(
    AutoModelForCausalLM.from_pretrained(BASE, torch_dtype=torch.bfloat16, device_map="auto"),
    "aaryand/qwen3-1.7b-context-adherence-guardrail").eval()

RUBRIC = """You are a groundedness guardrail for retrieval-augmented generation. \
Judge whether the RESPONSE is fully supported by the CONTEXT.

Rules:
- Verdict FAIL if the response makes at least one factual claim that is unsupported \
by or contradicts the context. Whether a claim is true in the real world is \
irrelevant: a claim absent from the context is still unsupported (FAIL).
- Verdict PASS otherwise. A response that declines to answer or says the context \
lacks the information is faithful (PASS)."""

def judge(question, context, response):
    body = (f"QUESTION: {question}\n\n" if question else "") + \
           f"CONTEXT:\n{context[:24000]}\n\nRESPONSE:\n{response}"
    prompt = f"{RUBRIC}\n\n{body}\nAnswer with exactly one word: PASS or FAIL."
    ids = tok.apply_chat_template([{"role": "user", "content": prompt}],
                                  add_generation_prompt=True, return_tensors="pt",
                                  enable_thinking=False).to(model.device)
    with torch.no_grad():
        logits = model(ids).logits[0, -1]
    p = torch.softmax(logits[[tok.encode("PASS")[0], tok.encode("FAIL")[0]]].float(), -1)
    return ("FAIL" if p[1] > p[0] else "PASS"), p[1].item()   # verdict, P(FAIL)

print(judge("Who wrote it?", "The report was written by Dr. Chen in 2019.",
            "Dr. Chen wrote it in 2019, and she also won a Nobel Prize."))
# ('FAIL', 0.9...) — the Nobel claim is absent from the context

Training

QLoRA NF4, LoRA r=16 / alpha=32 on all-linear targets, 2 epochs, lr 1e-4 cosine, effective batch 16, max 4096 tokens, one A100-40GB. Data: 10,710 items, 50/50 PASS/FAIL — see the dataset.

The verdict token is not fed as input: the model sees the prompt and the loss is cross-entropy at the final position against PASS/FAIL. That is bit-for-bit the quantity the eval scores, so training and evaluation are the same measurement rather than two that merely agree.

Minimum viable dataset size ~ 4,000. Marginal return per doubling: +0.017 (250->1k), +0.048 (1k->4k), then +0.0088 (4k->10,710). This checkpoint uses all 10,710 because it is the best measured model, but the curve stops paying for itself near 4,000.

Limitations

• Robustness gains less than half the headline. +0.081 worst-set against +0.162 pooled. Better on average, only modestly better on the distribution it handles worst. Size deployment risk from the robustness number.
• Under-flags. Recall 0.53 on the hard scenarios — it misses roughly half of subtle hallucinations there. A precision instrument, not a safety net.
• One metric, one context. Grounding only. Says nothing about toxicity, prompt injection, or tool selection.
• In-domain parity is not general-judge parity. Trained on RAGTruth-train; RAGTruth-test shares its annotation conventions and generator distribution.
• Not calibrated. ECE was never computed. Treat P(FAIL) as an ordering, not a probability.
• No adversarial evaluation. Untested against jailbreaks or over-defense probes.
• Single seed. Seed variance was not measured; curve differences below ~0.01 are noise.

Reproduce

pip install torch transformers peft accelerate
python eval.py --model aaryand/qwen3-1.7b-context-adherence-guardrail --baseline
python eval.py --model aaryand/qwen3-1.7b-context-adherence-guardrail --eval-set your_set.jsonl

Code, raw transcripts for all 19 eval runs, ablation scripts and training logs are in the project repository. Eval-code commit: b5467d033690f3909cfacfd69bfb3fa04cc6a946.