metadata

base_model: BAAI/bge-base-en-v1.5
language:
  - en
library_name: sentence-transformers
license: apache-2.0
metrics:
  - cosine_accuracy@1
  - cosine_accuracy@3
  - cosine_accuracy@5
  - cosine_accuracy@10
  - cosine_precision@1
  - cosine_precision@3
  - cosine_precision@5
  - cosine_precision@10
  - cosine_recall@1
  - cosine_recall@3
  - cosine_recall@5
  - cosine_recall@10
  - cosine_ndcg@10
  - cosine_mrr@10
  - cosine_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:6300
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: >-
      The consolidated financial statements and accompanying notes listed in
      Part IV, Item 15(a)(1) of this Annual Report on Form 10-K are included
      elsewhere in this Annual Report on Form 10-K.
    sentences:
      - >-
        What is the carrying value of the indefinite-lived intangible assets
        related to the Certificate of Needs and Medicare licenses as of December
        31, 2023?
      - >-
        What sections of the Annual Report on Form 10-K contain the company's
        financial statements?
      - >-
        What was the effective tax rate excluding discrete net tax benefits for
        the year 2022?
  - source_sentence: >-
      Consumers are served through Amazon's online and physical stores with an
      emphasis on selection, price, and convenience.
    sentences:
      - >-
        What decision did the European Commission make on July 10, 2023
        regarding the United States?
      - >-
        What are the primary offerings to consumers through Amazon's online and
        physical stores?
      - >-
        What activities are included in the services and other revenue segment
        of General Motors Company?
  - source_sentence: >-
      Visa has traditionally referred to their structure of facilitating secure,
      reliable, and efficient money movement among consumers, issuing and
      acquiring financial institutions, and merchants as the 'four-party' model.
    sentences:
      - >-
        What model does Visa traditionally refer to regarding their transaction
        process among consumers, financial institutions, and merchants?
      - >-
        What percentage of Meta's U.S. workforce in 2023 were represented by
        people with disabilities, veterans, and members of the LGBTQ+ community?
      - >-
        What are the revenue sources for the Company’s Health Care Benefits
        Segment?
  - source_sentence: >-
      In addition to LinkedIn’s free services, LinkedIn offers monetized
      solutions: Talent Solutions, Marketing Solutions, Premium Subscriptions,
      and Sales Solutions. Talent Solutions provide insights for workforce
      planning and tools to hire, nurture, and develop talent. Talent Solutions
      also includes Learning Solutions, which help businesses close critical
      skills gaps in times where companies are having to do more with existing
      talent.
    sentences:
      - >-
        What were the major factors contributing to the increased expenses
        excluding interest for Investor Services and Advisor Services in 2023?
      - >-
        What were the pre-tax earnings of the manufacturing sector in 2023,
        2022, and 2021?
      - What does LinkedIn's Talent Solutions include?
  - source_sentence: >-
      Management assessed the effectiveness of the company’s internal control
      over financial reporting as of December 31, 2023. In making this
      assessment, we used the criteria set forth by the Committee of Sponsoring
      Organizations of the Treadway Commission (COSO) in Internal
      Control—Integrated Framework (2013).
    sentences:
      - >-
        What criteria did Caterpillar Inc. use to assess the effectiveness of
        its internal control over financial reporting as of December 31, 2023?
      - What are the primary components of U.S. sales volumes for Ford?
      - >-
        What was the percentage increase in Schwab's common stock dividend in
        2022?
model-index:
  - name: BGE base Financial Matryoshka
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.69
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8385714285714285
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.87
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.92
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.69
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27952380952380956
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.174
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09199999999999998
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.69
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8385714285714285
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.87
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.92
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8078047173747194
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7717607709750567
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7745029834237301
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 512
          type: dim_512
        metrics:
          - type: cosine_accuracy@1
            value: 0.7014285714285714
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8342857142857143
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8671428571428571
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.9171428571428571
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.7014285714285714
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.27809523809523806
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1734285714285714
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.09171428571428569
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.7014285714285714
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8342857142857143
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8671428571428571
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.9171428571428571
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8099294101814819
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.775592970521542
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7785490266159816
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 256
          type: dim_256
        metrics:
          - type: cosine_accuracy@1
            value: 0.6928571428571428
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8285714285714286
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.8614285714285714
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.91
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6928571428571428
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2761904761904762
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.17228571428571426
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.091
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6928571428571428
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8285714285714286
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.8614285714285714
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.91
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.8023495466461429
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7679013605442175
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7712468743892164
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 128
          type: dim_128
        metrics:
          - type: cosine_accuracy@1
            value: 0.6728571428571428
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.8171428571428572
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.85
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8828571428571429
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.6728571428571428
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.2723809523809524
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16999999999999998
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08828571428571429
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.6728571428571428
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.8171428571428572
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.85
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8828571428571429
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7823204493781594
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7495634920634917
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.75425425293366
            name: Cosine Map@100
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 64
          type: dim_64
        metrics:
          - type: cosine_accuracy@1
            value: 0.64
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.79
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.83
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.8742857142857143
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.64
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.26333333333333336
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.16599999999999998
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08742857142857141
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.64
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.79
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.83
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.8742857142857143
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.7602361447545036
            name: Cosine Ndcg@10
          - type: cosine_mrr@10
            value: 0.7233747165532877
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.7278552309882971
            name: Cosine Map@100

BGE base Financial Matryoshka

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5 on the json dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: BAAI/bge-base-en-v1.5
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- json
Language: en
License: apache-2.0

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': True}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sh4796/bge-base-financial-matryoshka")
# Run inference
sentences = [
    'Management assessed the effectiveness of the company’s internal control over financial reporting as of December 31, 2023. In making this assessment, we used the criteria set forth by the Committee of Sponsoring Organizations of the Treadway Commission (COSO) in Internal Control—Integrated Framework (2013).',
    'What criteria did Caterpillar Inc. use to assess the effectiveness of its internal control over financial reporting as of December 31, 2023?',
    'What are the primary components of U.S. sales volumes for Ford?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Information Retrieval

Dataset: dim_768
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.69
cosine_accuracy@3	0.8386
cosine_accuracy@5	0.87
cosine_accuracy@10	0.92
cosine_precision@1	0.69
cosine_precision@3	0.2795
cosine_precision@5	0.174
cosine_precision@10	0.092
cosine_recall@1	0.69
cosine_recall@3	0.8386
cosine_recall@5	0.87
cosine_recall@10	0.92
cosine_ndcg@10	0.8078
cosine_mrr@10	0.7718
cosine_map@100	0.7745

Information Retrieval

Dataset: dim_512
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.7014
cosine_accuracy@3	0.8343
cosine_accuracy@5	0.8671
cosine_accuracy@10	0.9171
cosine_precision@1	0.7014
cosine_precision@3	0.2781
cosine_precision@5	0.1734
cosine_precision@10	0.0917
cosine_recall@1	0.7014
cosine_recall@3	0.8343
cosine_recall@5	0.8671
cosine_recall@10	0.9171
cosine_ndcg@10	0.8099
cosine_mrr@10	0.7756
cosine_map@100	0.7785

Information Retrieval

Dataset: dim_256
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6929
cosine_accuracy@3	0.8286
cosine_accuracy@5	0.8614
cosine_accuracy@10	0.91
cosine_precision@1	0.6929
cosine_precision@3	0.2762
cosine_precision@5	0.1723
cosine_precision@10	0.091
cosine_recall@1	0.6929
cosine_recall@3	0.8286
cosine_recall@5	0.8614
cosine_recall@10	0.91
cosine_ndcg@10	0.8023
cosine_mrr@10	0.7679
cosine_map@100	0.7712

Information Retrieval

Dataset: dim_128
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.6729
cosine_accuracy@3	0.8171
cosine_accuracy@5	0.85
cosine_accuracy@10	0.8829
cosine_precision@1	0.6729
cosine_precision@3	0.2724
cosine_precision@5	0.17
cosine_precision@10	0.0883
cosine_recall@1	0.6729
cosine_recall@3	0.8171
cosine_recall@5	0.85
cosine_recall@10	0.8829
cosine_ndcg@10	0.7823
cosine_mrr@10	0.7496
cosine_map@100	0.7543

Information Retrieval

Dataset: dim_64
Evaluated with InformationRetrievalEvaluator

Metric	Value
cosine_accuracy@1	0.64
cosine_accuracy@3	0.79
cosine_accuracy@5	0.83
cosine_accuracy@10	0.8743
cosine_precision@1	0.64
cosine_precision@3	0.2633
cosine_precision@5	0.166
cosine_precision@10	0.0874
cosine_recall@1	0.64
cosine_recall@3	0.79
cosine_recall@5	0.83
cosine_recall@10	0.8743
cosine_ndcg@10	0.7602
cosine_mrr@10	0.7234
cosine_map@100	0.7279

Training Details

Training Dataset

json

Dataset: json
Size: 6,300 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 8 tokens
mean: 44.33 tokens
max: 289 tokens

min: 9 tokens
mean: 20.43 tokens
max: 46 tokens

	positive	anchor
type	string	string
details	min: 8 tokens mean: 44.33 tokens max: 289 tokens	min: 9 tokens mean: 20.43 tokens max: 46 tokens

Samples:

positive	anchor
The Company defines fair value as the price received to transfer an asset or paid to transfer a liability in an orderly transaction between market participants at the measurement date. In accordance with ASC 820, Fair Value Measurements and Disclosures, the Company uses the fair value hierarchy which prioritizes the inputs used to measure fair value. The hierarchy gives the highest priority to unadjusted quoted prices in active markets for identical assets or liabilities (Level 1), observable inputs other than quoted prices (Level 2), and unobservable inputs (Level 3).	`What is the role of Level 1, Level 2, and Level 3 inputs in the fair value hierarchy according to ASC 820?`
`In the event of conversion of the Notes, if shares are delivered to the Company under the Capped Call Transactions, they will offset the dilutive effect of the shares that the Company would issue under the Notes.`	`What happens to the dilutive effect of shares issued under the Notes if shares are delivered to the Company under the Capped Call Transactions during the conversion?`
`Marketing expenses increased $48.8 million to $759.2 million in the year ended December 31, 2023 compared to the year ended December 31, 2022.`	`How much did the marketing expenses increase in the year ended December 31, 2023?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768,
        512,
        256,
        128,
        64
    ],
    "matryoshka_weights": [
        1,
        1,
        1,
        1,
        1
    ],
    "n_dims_per_step": -1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: epoch
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
gradient_accumulation_steps: 16
learning_rate: 2e-05
num_train_epochs: 4
lr_scheduler_type: cosine
warmup_ratio: 0.1
bf16: True
tf32: True
load_best_model_at_end: True
optim: adamw_torch_fused
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: epoch
prediction_loss_only: True
per_device_train_batch_size: 32
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 16
eval_accumulation_steps: None
learning_rate: 2e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: True
fp16: False
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: True
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: True
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch_fused
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: None
hub_strategy: every_save
hub_private_repo: False
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	dim_768_cosine_map@100	dim_512_cosine_map@100	dim_256_cosine_map@100	dim_128_cosine_map@100	dim_64_cosine_map@100
0.8122	10	1.5604	-	-	-	-	-
0.9746	12	-	0.7538	0.7540	0.7483	0.7284	0.6906
1.6244	20	0.6618	-	-	-	-	-
1.9492	24	-	0.7654	0.7632	0.7582	0.7424	0.7186
2.4365	30	0.4579	-	-	-	-	-
2.9239	36	-	0.7686	0.7646	0.7619	0.7459	0.7238
3.2487	40	0.3995	-	-	-	-	-
3.8985	48	-	0.7694	0.7633	0.7641	0.7449	0.7225
0.8122	10	0.3798	-	-	-	-	-
0.9746	12	-	0.7713	0.7685	0.7691	0.7489	0.7249
1.6244	20	0.2958	-	-	-	-	-
1.9492	24	-	0.7726	0.7699	0.7688	0.7517	0.7283
2.4365	30	0.2273	-	-	-	-	-
2.9239	36	-	0.7742	0.7761	0.7734	0.7532	0.7276
3.2487	40	0.2136	-	-	-	-	-
3.8985	48	-	0.7745	0.7785	0.7712	0.7543	0.7279

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
Sentence Transformers: 3.2.0
Transformers: 4.41.2
PyTorch: 2.2.0a0+6a974be
Accelerate: 0.27.0
Datasets: 2.19.1
Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}