---
license: apache-2.0
base_model: allenai/OLMo-2-1124-7B
library_name: transformers
pipeline_tag: text-generation
language:
  - en
  - de
  - id
  - pt
  - ar
  - bn
  - sw
  - es
  - ru
  - fr
  - ja
  - zh
datasets:
  - jvonrad/WIKI-FACT
  - jvonrad/PolyFact
tags:
  - multilingual
  - cross-lingual
  - factual-recall
  - cross-lingual-consistency
  - dpo
  - cm-align
---

# OLMo-2-7B CM-Align (EN-pivot DPO)

`allenai/OLMo-2-1124-7B` post-trained with **CM-Align**, an English-pivot preference-alignment
method, as a **baseline** in a study of cross-lingual factual recall and consistency.

This is the OLMo counterpart of [`jvonrad/Qwen-2.5-CM-Align`](https://huggingface.co/jvonrad/Qwen-2.5-CM-Align).
Weights are **merged** (LoRA adapter folded into the base model), so it loads like any
standard OLMo-2 checkpoint.

## Method

Adaptation of CM-Align (Zhang et al., EMNLP 2025 Findings, [arXiv:2509.08541](https://arxiv.org/abs/2509.08541))
to a parallel multilingual factual-QA setting. The procedure is **self-supervised — it never uses
gold answer labels**:

1. **Preference construction.** For each fact, sample `K=4` free-text answers per language
   (temperature 0.9, top-p 0.95). Embed all candidates with
   [`sentence-transformers/LaBSE`](https://huggingface.co/sentence-transformers/LaBSE).
   Choose as **pivot** the most self-consistent English candidate (highest mean cosine
   similarity to the other English candidates). Then, for every other language, take
   `chosen = argmax` and `rejected = argmin` cosine similarity to that English pivot.
2. **DPO training.** Hand-rolled DPO on those preference pairs. The reference distribution is
   the *same* model with the LoRA adapter disabled, so no second copy of the model is held in
   memory. Objective: `L_DPO + gamma * L_NLL`.

CM-Align's original embedder was `gte-multilingual-base`; LaBSE is used here because it is the
cross-lingual encoder used throughout this project.

## Training details

| | |
|---|---|
| Base model | `allenai/OLMo-2-1124-7B` |
| Data | 40,000 facts from [`jvonrad/WIKI-FACT`](https://huggingface.co/datasets/jvonrad/WIKI-FACT) (train) |
| Languages | 12 — en, de, id, pt, ar, bn, sw, es, ru, fr, ja, zh |
| Candidates / language | 4 (temperature 0.9, top-p 0.95) |
| Embedder | `sentence-transformers/LaBSE` |
| DPO beta | 0.1 |
| NLL gamma | 0.0 |
| Learning rate | 5e-6 |
| Epochs | 1 |
| Batch size | 4 x 4 grad-accum |
| Precision | bf16 |
| LoRA | r=64, alpha=128, dropout=0.05, on q/k/v/o/gate/up/down projections |
| Reference model | same model, adapter disabled (`disable_adapter()`) |

## Evaluation

Answers are scored by length-normalised log-likelihood over the four options, with the plain
prompt `Question: {question}\nAnswer:`. Metrics beyond accuracy:

- **TotCons** (Total Consistency) — fraction of facts answered correctly in *all* languages.
- **RankC** — cross-lingual agreement between full option rankings (Qi et al., EMNLP 2023).
- **AnsAgr** — pairwise answer agreement across language pairs.

**PolyFact test** (2,523 facts, 12 languages):

| Model | Acc | TotCons | RankC | AnsAgr |
|---|---|---|---|---|
| OLMo-2-7B (base) | 57.96 | 7.21 | 58.32 | 51.10 |
| **OLMo-2-7B CM-Align** | **60.44** | **9.35** | **60.07** | **53.41** |

**Global-MMLU-Lite** (400 facts, 11 languages — Lite has no Russian config):

| Model | Acc | TotCons | RankC | AnsAgr |
|---|---|---|---|---|
| OLMo-2-7B (base) | 44.75 | **3.50** | 55.12 | 46.48 |
| **OLMo-2-7B CM-Align** | 42.93 | 2.50 | **57.31** | **48.45** |

Per-language accuracy on PolyFact test:

| en | de | id | pt | ar | bn | sw | es | ru | fr | ja | zh |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 80.6 | 71.3 | 68.8 | 69.6 | 45.1 | 42.3 | 47.6 | 71.9 | 55.6 | 72.3 | 51.0 | 49.1 |

### Reading these numbers

CM-Align gives consistent **in-domain** gains over the base model on PolyFact (all four metrics).
**Out of domain** on Global-MMLU-Lite the picture is mixed: cross-lingual agreement improves
(RankC +2.19, AnsAgr +1.97) but accuracy and total consistency drop slightly. This model is
published as a **baseline for comparison**, not as a recommended general-purpose checkpoint.

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "jvonrad/OLMo-2-7B-CM-Align"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16", device_map="auto")

prompt = "Question: What is the capital of Poland?\nAnswer:"
out = model.generate(**tok(prompt, return_tensors="pt").to(model.device), max_new_tokens=16)
print(tok.decode(out[0], skip_special_tokens=True))
```

This is a **base (non-instruct) model** — it has no chat template. Use plain completion-style
prompts such as the `Question: ... \nAnswer:` form above.

## Limitations

- Trained only on Wikidata-derived factual QA in 12 languages; it is not a general instruction-following model.
- Preference pairs are built from the model's own samples via embedding similarity, so they
  inherit LaBSE's similarity biases and can reward fluent-but-wrong answers.
- Improved cross-lingual consistency can make *incorrect* factual associations more uniform
  across languages as well as correct ones.
- Evaluation is multiple-choice log-likelihood scoring; it does not measure free-form generation quality.

## Citation

The CM-Align method this baseline implements:

```bibtex
@inproceedings{zhang2025cmalign,
  title     = {CM-Align: Consistency-based Multilingual Alignment for Large Language Models},
  author    = {Zhang, Xue and others},
  booktitle = {Findings of EMNLP},
  year      = {2025}
}
```

The RankC consistency metric used above:

```bibtex
@inproceedings{qi2023crosslingual,
  title     = {Cross-Lingual Consistency of Factual Knowledge in Multilingual Language Models},
  author    = {Qi, Jirui and Fern{\'a}ndez, Raquel and Bisazza, Arianna},
  booktitle = {EMNLP},
  year      = {2023}
}
```