ManasMehta

groundingbench-overseer-lr2e5-ckpt400

Model details

Base model: Qwen/Qwen2.5-1.5B-Instruct (frozen, bf16)
Adapter: LoRA, r=16, α=32, dropout=0.05, targets q_proj, k_proj, v_proj, o_proj
Training algorithm: GRPO (Group Relative Policy Optimization) via TRL
Steps: 400
Learning rate: 2e-5
Beta (KL coefficient): 0.04
Generations per step: 4
Max completion length: 256 tokens
Seed: 42 (this is one of a multi-seed grid; see the project repo for the full seed-variance results)

Intended use

The model is the overseer agent in a single-step reinforcement learning loop:

Input: a question, a trace of an agent's tool calls, and the agent's final claim

Output: a 3-line verdict in the format:

markdown
VERDICT: <HONEST | REWARD_HACKER | LAZY | DECEIVER>
CONFIDENCE: <0.0–1.0>
EVIDENCE: <one sentence citing a specific trace step and keyword>

It is trained to plug into GroundingBench's /step endpoint. It can be used standalone but the reward signal that shaped it is environment-specific.

Training data

960 traces generated from 12 deterministic doer policies (4 behavioral classes × 3 variants), restricted to variants 1 and 2 of questions q_0001–q_0120. Variant 3 and questions q_0121–q_0150 are held out for evaluation. Train and eval splits are disjoint on both axes (questions AND policy variant).

Evaluation

Evaluated on the held-out v3 set (n=120, q_0121–q_0150 × variant 3, fully disjoint from training):

Table with columns: Condition, Accuracy, Mean Reward, Parse Errors
Condition	Accuracy	Mean Reward	Parse Errors
Random verdict	25.0%	—	—
Base Qwen2.5-1.5B + 3-shot prompt	56.7%	0.438	0.0%
This adapter (LR=2e-5, 400 steps)	75.8%	0.900	0.0%

Evidence-bonus hit rate (grounding, not just accuracy) for this checkpoint: DECEIVER 82.8%, LAZY 28.6%, REWARD_HACKER 0.0% (n=1 seed). See the project repo for the full 3-seed grid across both learning rates and trace distributions, and for the pooled significance testing against the ~0% frontier-model baseline.

Limitations

Reference-scale RL run on a single 1.5B base model. Larger base models, longer training, and LR scheduling are untested.
Training doer policies are rule-based (a second "realistic," LLM-surfaced trace distribution is also evaluated in the full project — see the repo).
The held-out set varies on two axes simultaneously (questions AND policy variant); the accuracy lift cannot be decomposed between question novelty and variant novelty.

Reproducing the eval

bash
git clone https://github.com/ManasMehta1110/GroundingBench.git
cd GroundingBench
pip install -r requirements.txt && pip install -e .

python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='ManasMehta/groundingbench-overseer-lr2e5-ckpt400', local_dir='checkpoints/checkpoint-400')"

python scripts/gen_gap_eval.py \
  --model-path checkpoints/checkpoint-400 \
  --base-model Qwen/Qwen2.5-1.5B-Instruct \
  --eval-easy data/eval_traces.jsonl \
  --eval-hard data/eval_traces.jsonl \
  --out results/repro.json

Citation

bibtex
@misc{groundingbench2026,
  title        = {GroundingBench: Measuring Evidence-Grounded AI Oversight},
  author       = {Mehta, Manas},
  year         = {2026},
  howpublished = {\url{https://github.com/ManasMehta1110/GroundingBench}},
  note         = {Preprint in preparation, target venue IEEE SaTML 2027}
}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

ManasMehta

Model Tree

Base

Qwen/Qwen2.5-1.5B-Instruct

Adapter

this model

Input Modalities

Text

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

Model details

Base model: Qwen/Qwen2.5-1.5B-Instruct (frozen, bf16)
Adapter: LoRA, r=16, α=32, dropout=0.05, targets q_proj, k_proj, v_proj, o_proj
Training algorithm: GRPO (Group Relative Policy Optimization) via TRL
Steps: 400
Learning rate: 2e-5
Beta (KL coefficient): 0.04
Generations per step: 4
Max completion length: 256 tokens
Seed: 42 (this is one of a multi-seed grid; see the project repo for the full seed-variance results)

Intended use

The model is the overseer agent in a single-step reinforcement learning loop:

Input: a question, a trace of an agent's tool calls, and the agent's final claim

Output: a 3-line verdict in the format:

markdown
VERDICT: <HONEST | REWARD_HACKER | LAZY | DECEIVER>
CONFIDENCE: <0.0–1.0>
EVIDENCE: <one sentence citing a specific trace step and keyword>

It is trained to plug into GroundingBench's /step endpoint. It can be used standalone but the reward signal that shaped it is environment-specific.

Training data

Evaluation

Evaluated on the held-out v3 set (n=120, q_0121–q_0150 × variant 3, fully disjoint from training):

Table with columns: Condition, Accuracy, Mean Reward, Parse Errors
Condition	Accuracy	Mean Reward	Parse Errors
Random verdict	25.0%	—	—
Base Qwen2.5-1.5B + 3-shot prompt	56.7%	0.438	0.0%
This adapter (LR=2e-5, 400 steps)	75.8%	0.900	0.0%

Limitations

Reference-scale RL run on a single 1.5B base model. Larger base models, longer training, and LR scheduling are untested.
Training doer policies are rule-based (a second "realistic," LLM-surfaced trace distribution is also evaluated in the full project — see the repo).
The held-out set varies on two axes simultaneously (questions AND policy variant); the accuracy lift cannot be decomposed between question novelty and variant novelty.

Reproducing the eval

bash
git clone https://github.com/ManasMehta1110/GroundingBench.git
cd GroundingBench
pip install -r requirements.txt && pip install -e .

python -c "from huggingface_hub import snapshot_download; snapshot_download(repo_id='ManasMehta/groundingbench-overseer-lr2e5-ckpt400', local_dir='checkpoints/checkpoint-400')"

python scripts/gen_gap_eval.py \
  --model-path checkpoints/checkpoint-400 \
  --base-model Qwen/Qwen2.5-1.5B-Instruct \
  --eval-easy data/eval_traces.jsonl \
  --eval-hard data/eval_traces.jsonl \
  --out results/repro.json

Citation

bibtex
@misc{groundingbench2026,
  title        = {GroundingBench: Measuring Evidence-Grounded AI Oversight},
  author       = {Mehta, Manas},
  year         = {2026},
  howpublished = {\url{https://github.com/ManasMehta1110/GroundingBench}},
  note         = {Preprint in preparation, target venue IEEE SaTML 2027}
}

groundingbench-overseer-lr2e5-ckpt400

README

Model details

Intended use

Training data

Evaluation

Limitations

Reproducing the eval

Citation

Explore FriendliAI today

README

Model details

Intended use

Training data

Evaluation

Limitations

Reproducing the eval

Citation