metadata

base_model: BAAI/bge-base-en-v1.5
datasets: []
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_ndcg@100
  - cosine_mrr@10
  - cosine_map@100
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:9000
  - loss:MatryoshkaLoss
  - loss:MultipleNegativesRankingLoss
widget:
  - source_sentence: ' and Banking and Securities Services, and that helps us in FX, in commodities and in rates around the world. So, Markets is important both in terms of its leadership, but also, how it fits into the strengths that we have from this simpler Citi of those five core interconnected businesses. We''ve demonstrated solid returns in the past. I think a lot of the actions we''ve been taking will help drive returns in the future. And you should be getting confidence when you see the discipline we''re putting on to Copyright 2024 Citigroup Inc. 14 TRANSCRIPT Citi Fourth Quarter 2023 Earnings Call January 12, 2024 RWA, 5.3, getting close that target, we said at Investor Day. We''re moving that up to 6. The exits we''ve got of nonstrategic businesses shows our focus on efficiency. And we''ve also been doing some good investments in our technology, and that''s getting us into a good place there. So'
    sentences:
      - >-
        What are the strengths and importance of Markets in terms of leadership
        and its role in the interconnected businesses of Citigroup Inc?
      - >-
        What are the additional resources available to help assess current
        finances and plan for the future?
      - >-
        ¿Puedo cerrar mi cuenta en cualquier momento y sin restricciones? ¿Qué
        sucede si mi cuenta tiene un saldo de cero durante 90 días consecutivos?
        ¿Puedo obtener copias de cheques cancelados o imágenes de los mismos en
        mi estado de cuenta? ¿Debo llamar a CitiPhone Banking para solicitar las
        imágenes de los cheques? ¿Existen comisiones adicionales o cargos
        asociados con esto? ¿Puedo acceder a las imágenes de los cheques en
        línea y imprimirlos sin ningún costo adicional en citibankonline.com?
  - source_sentence: ' legal, investment, or financial advice and is not a substitute for professional advice. It does not indicate the availability of any Citi product or service. For advice about your specific circumstances, you should consult a qualified professional. Additional Resources - ! Insights and Tools Utilize these resources to help you assess your current finances plan for the future. - ! FICO Score Learn how FICO Scores are determined, why they matter and more. - ! Glossary Review financial terms definitions to help you better understand credit finances. !Back to Top Back to Top !Equal housing lender Contact Us - Consumer: 1-800-347-4934 - Consumer TTY: 711 - Business: 1-866-422-3091 - Business TTY: 711 - LostStolen: 1-800-950-5114 - LostStolen TTY: 711 About Us - Locations - Careers - Site Map Terms Conditions - Card Member Agreement - Security - Privacy - Notice At Collection -'
    sentences:
      - >-
        What are the key steps in the tailor consultative process for wealth
        advisory services to create a broad plan for the client's future?
      - >-
        What are the benefits and program details of the American Airlines
        AAdvantage MileUp Card? Can I earn AAdvantage miles for flights,
        upgrades, car rentals, hotel stays, or vacation packages? How many
        AAdvantage miles can I earn at grocery stores, including grocery
        delivery services? How many AAdvantage miles can I earn on eligible
        American Airlines purchases? How many AAdvantage miles can I earn on all
        other purchases? Can I earn loyalty points for eligible mile purchases?
        How many loyalty points can I earn?
      - >-
        What resources are available to help assess current finances and plan
        for the future?
  - source_sentence: ' Watchlist Alerts . 17 Delivery Settings and Hold Alerts for Brokerage Alerts . 18 5. Electronic Delivery . 19 Add E-mail Addresses . 19 Set Up e-Delivery for an Individual Account . 20 3 Set Up e-Delivery for Multiple Accounts using Quick Enroll. 20 View Statements Reports. 21 View Trade Confirmations. 21 View Tax Documents . 22 View Notifications . 22 6. Account Portfolio . 24 Overview . 24 Portfolio Changes . 24 Quick Links . 25 Composition of Holdings . 25 Quick Trade . 25 Open Orders Executed Trades . 25 Strong Weak Performers . 26 Portfolio History . 26 News. 27 Balances . 28 Holdings . 29 Non Dollar transactions on Non US exchanges valued at foreign currency of the exchange . 30 Realized GainLoss . 32 History . 34 Projected Cash Flow. 35 7. Transact . 36 Trade Equities . '
    sentences:
      - >-
        What is the track record of the company in managing the risks associated
        with its global network and what is its business model focused on?
      - >-
        What are the watchlist alerts for brokerage alerts and how can
        electronic delivery be set up for an individual account and multiple
        accounts using quick enroll? How can statements reports, trade
        confirmations, tax documents, and notifications be viewed? What is the
        overview of the account portfolio and how can portfolio changes, quick
        links, composition of holdings, quick trades, open orders executed
        trades, strong weak performers, portfolio history, news, balances,
        holdings, non-dollar transactions on non-US exchanges valued at foreign
        currency of the exchange, realized gain/loss, history, and projected
        cash flow be accessed? How can equities be traded?
      - What does the EMV chip do and how does it work?
  - source_sentence: >-
      . Los productos y servicios mencionados en este documento no se ofrecen a
      individuos que residen en la Unin Europea, el Espacio Econmico Europeo,
      Suiza, Guernsey, Jersey, Mnaco, Isla de Man, San Marino y el Vaticano. Su
      elegibilidad para productos y servicios en particular est sujeta a una
      decisin definitiva de nuestra parte. Este documento no es ni debe
      interpretarse como si fuera una oferta, invitacin o solicitud para comprar
      o vender alguno de los productos y servicios mencionados aqu a tales
      personas. 2020 Citibank, N.A., Miembro FDIC. Citi, Citi con el Diseo del
      Arco y las otras marcas usadas en el presente documento son marcas de
      servicio de Citigroup Inc. o sus filiales, usadas y registradas en todo el
      mundo. Todos los derechos reservados. IFCBRO-0320SP Treasury
    sentences:
      - >-
        exime Citibank este cargo para cuentas Citigold cheques de diseo estndar
        para todas Pedidos de chequeras, cheques oficiales, entrega rpida en el
        pas de tarjetas de dbito de reemplazo, giro para clientes, cargos por
        investigacin y proceso de verificacin consular o carta de referencia,
        cumplimiento de proceso legal y servicios de cobranza. También exime
        Citibank este cargo para cuentas Citigold en el caso de canje de cupones
        de bonos.
      - >-
        What are the products and services mentioned in this document and where
        are they offered? Can individuals residing in the European Union, the
        European Economic Area, Switzerland, Guernsey, Jersey, Monaco, Isle of
        Man, San Marino, and the Vatican avail these products and services? Is
        this document an offer, invitation, or solicitation to buy or sell any
        of the mentioned products and services to such individuals? Which
        organization owns the trademarks and service marks used in this
        document?
      - >-
        How can credit card points be redeemed for cash and what can the cash be
        used for?
  - source_sentence: ' Drive, Attn: Arbitration Opt Out, San Antonio, TX 78245. Your rejection notice must be mailed within 45 days of account opening. Your rejection notice must state that you reject the arbitration provision and include your name, address, account number and personal signature. No one else may sign the rejection notice. Your rejection notice will not apply to the arbitration provision governing any other account that you have or had with us. Rejection of this arbitration provision wont affect your other rights or responsibilities under this Agreement, including use of the account. 68 Appendix 1: Fee Schedule The following Checkbook Order Fee, Safe Deposit Fee, Fee Chart, and Wire Transfer Fee Chart are known as the Fee Schedule. Unless otherwise stated, all fees described in the Fee Schedule are charged to the account associated with the product or service. Checkbook Orders. Fees will be charged for standard and Non-Standard checkbook orders. Non-Standard Checkbook Orders include non-standard design, non-standard lettering'
    sentences:
      - How can I start building credit?
      - >-
        What is the Annual Percentage Yield for the Citigold Private Client
        Pendant Exclusive 24K Gold Rabbit on the Moon or IL in the states of NY,
        CT, MD, VA, DC, CA, NV, NJ and select markets in FL?
      - >-
        What is the process for rejecting the arbitration provision and what
        information should be included in the rejection notice?
model-index:
  - name: SentenceTransformer based on BAAI/bge-base-en-v1.5
    results:
      - task:
          type: information-retrieval
          name: Information Retrieval
        dataset:
          name: dim 768
          type: dim_768
        metrics:
          - type: cosine_accuracy@1
            value: 0.524
            name: Cosine Accuracy@1
          - type: cosine_accuracy@3
            value: 0.718
            name: Cosine Accuracy@3
          - type: cosine_accuracy@5
            value: 0.7826666666666666
            name: Cosine Accuracy@5
          - type: cosine_accuracy@10
            value: 0.848
            name: Cosine Accuracy@10
          - type: cosine_precision@1
            value: 0.524
            name: Cosine Precision@1
          - type: cosine_precision@3
            value: 0.23933333333333334
            name: Cosine Precision@3
          - type: cosine_precision@5
            value: 0.1565333333333333
            name: Cosine Precision@5
          - type: cosine_precision@10
            value: 0.08479999999999999
            name: Cosine Precision@10
          - type: cosine_recall@1
            value: 0.524
            name: Cosine Recall@1
          - type: cosine_recall@3
            value: 0.718
            name: Cosine Recall@3
          - type: cosine_recall@5
            value: 0.7826666666666666
            name: Cosine Recall@5
          - type: cosine_recall@10
            value: 0.848
            name: Cosine Recall@10
          - type: cosine_ndcg@10
            value: 0.6849393771058847
            name: Cosine Ndcg@10
          - type: cosine_ndcg@100
            value: 0.7108472738066071
            name: Cosine Ndcg@100
          - type: cosine_mrr@10
            value: 0.6327346560846572
            name: Cosine Mrr@10
          - type: cosine_map@100
            value: 0.638367026629088
            name: Cosine Map@100

SentenceTransformer based on BAAI/bge-base-en-v1.5

This is a sentence-transformers model finetuned from BAAI/bge-base-en-v1.5. 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
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("MugheesAwan11/bge-base-citi-dataset-detailed-9k-1_5k-e1")
# Run inference
sentences = [
    ' Drive, Attn: Arbitration Opt Out, San Antonio, TX 78245. Your rejection notice must be mailed within 45 days of account opening. Your rejection notice must state that you reject the arbitration provision and include your name, address, account number and personal signature. No one else may sign the rejection notice. Your rejection notice will not apply to the arbitration provision governing any other account that you have or had with us. Rejection of this arbitration provision wont affect your other rights or responsibilities under this Agreement, including use of the account. 68 Appendix 1: Fee Schedule The following Checkbook Order Fee, Safe Deposit Fee, Fee Chart, and Wire Transfer Fee Chart are known as the Fee Schedule. Unless otherwise stated, all fees described in the Fee Schedule are charged to the account associated with the product or service. Checkbook Orders. Fees will be charged for standard and Non-Standard checkbook orders. Non-Standard Checkbook Orders include non-standard design, non-standard lettering',
    'What is the process for rejecting the arbitration provision and what information should be included in the rejection notice?',
    'What is the Annual Percentage Yield for the Citigold Private Client Pendant Exclusive 24K Gold Rabbit on the Moon or IL in the states of NY, CT, MD, VA, DC, CA, NV, NJ and select markets in FL?',
]
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	0.524
cosine_accuracy@3	0.718
cosine_accuracy@5	0.7827
cosine_accuracy@10	0.848
cosine_precision@1	0.524
cosine_precision@3	0.2393
cosine_precision@5	0.1565
cosine_precision@10	0.0848
cosine_recall@1	0.524
cosine_recall@3	0.718
cosine_recall@5	0.7827
cosine_recall@10	0.848
cosine_ndcg@10	0.6849
cosine_ndcg@100	0.7108
cosine_mrr@10	0.6327
cosine_map@100	0.6384

Training Details

Training Dataset

Unnamed Dataset

Size: 9,000 training samples
Columns: positive and anchor
Approximate statistics based on the first 1000 samples:
positive anchor
type string string
details
min: 152 tokens
mean: 206.96 tokens
max: 299 tokens

min: 9 tokens
mean: 52.08 tokens
max: 281 tokens

	positive	anchor
type	string	string
details	min: 152 tokens mean: 206.96 tokens max: 299 tokens	min: 9 tokens mean: 52.08 tokens max: 281 tokens

Samples:

positive	anchor
adverse effect on the value of any Index Linked Product. 15 Citi Investment Strategies Citi Flexible Allocation 6 Excess Return Index Index General Conditions Section D: Definitions 16 Citi Investment Strategies Citi Flexible Allocation 6 Excess Return Index Index General Conditions Definitions References to the "applicable Index Methodology" are references to the Index Methodology relating to the relevant Index which together with these Index General Conditions completes the Index Conditions for such Index. References to a "Section" shall be references to a section of these Index General Conditions. References to a "Part" shall be references to a part of the applicable Index Methodology. "Adjustment Event" shall, in respect of a Constituent, have the meaning given to it in the Constituent Schedule applicable to such Constituent. "Affected Constituent" shall have the meaning given to it in Section B . "Affiliate" shall mean, in respect of a person, any entity controlled by such person, any entity which controls	`What is the meaning of "applicable Index Methodology" in the Index General Conditions? What does "Section" refer to in the Index General Conditions? How is "Part" defined in the applicable Index Methodology? What is the definition of "Adjustment Event" in relation to a Constituent? How is an "Affected Constituent" defined in Section B? What is the definition of "Affiliate" in relation to a person?`
that the Depositary andor the Custodian may in the future identify from the balance of Shares on deposit in the DR program as belonging to the holders of DRs in the DR Balance on the basis of a full or partial reconciliation of the Share-to-DR imbalance created by the Automatic Conversions and Forced Conversions. The is no guarantee that any such reconciliation will be successful or that any such Shares will be available any time in the near or distant future, and as a result there is no indication that the DRs credited to the DR balance have, or will in the future have, any value. The creation of the DR Balance and any credit of DRs in the DR balance to a Beneficial Owner is purely an accommodation to the Beneficial Owner and does not represent any undertaking of any value or service. Neither the Depositary nor the Custodian undertake in any way to take any action on behalf of the holders of DRs credited to the DR balance to retrieve any Shares from third parties	What is the likelihood of the Depositary and/or the Custodian successfully reconciling the Share-to-DR imbalance in the DR program and identifying Shares belonging to DR holders in the DR Balance? Is there any guarantee of the availability or future value of these Shares? Are the DRs credited to the DR balance of any value? Does the creation of the DR Balance and credit of DRs to Beneficial Owners represent any commitment of value or service? Do the Depositary and the Custodian have any responsibility to retrieve Shares from third parties on behalf of DR holders credited to the DR balance?
of ways to save money while shopping online. Thats why a browser extension like Citi Shop can be a great addition to your online shopping experience. Lets look at how the Citi Shop extension works. Contact helpdeskciti.com What is the Citi Shop Browser Extension? Citi Shop is a free desktop browser extension you can download through the Chrome, Edge or Safari app stores. Once installed, enroll your eligible Citi credit card and let the Citi Shop program automatically search for available offers at more than 5,000 online merchants across the internet. How to Install the Citi Shop Browser Extension First, download the Citi Shop browser extension from the Chrome, Edge or Safari app store for your desktop browser. Once downloaded, you will be required to enroll your eligible Citi credit card. Contact helpdeskciti.com How to Use the Citi Shop Browser Extension Simply shop at your favorite online merchants. The Citi Shop program automatically searches behind the scenes to find money-saving offers percent	`What is the Citi Shop Browser Extension and how does it work? How can I install the Citi Shop Browser Extension for my desktop browser? How do I use the Citi Shop Browser Extension to save money while shopping online? Who can I contact for help with the Citi Shop Browser Extension?`

Loss: MatryoshkaLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "matryoshka_dims": [
        768
    ],
    "matryoshka_weights": [
        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
learning_rate: 2e-05
num_train_epochs: 2
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: 1
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: 2
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
0.0355	10	0.7377	-
0.0709	20	0.5614	-
0.1064	30	0.4571	-
0.1418	40	0.2944	-
0.1773	50	0.2584	-
0.2128	60	0.1855	-
0.2482	70	0.1699	-
0.2837	80	0.2212	-
0.3191	90	0.1827	-
0.3546	100	0.1801	-
0.3901	110	0.1836	-
0.4255	120	0.1112	-
0.4610	130	0.1638	-
0.4965	140	0.1355	-
0.5319	150	0.0873	-
0.5674	160	0.1852	-
0.6028	170	0.1424	-
0.6383	180	0.1467	-
0.6738	190	0.1879	-
0.7092	200	0.1382	-
0.7447	210	0.1358	-
0.7801	220	0.0906	-
0.8156	230	0.1173	-
0.8511	240	0.1196	-
0.8865	250	0.1251	-
0.9220	260	0.0922	-
0.9574	270	0.1344	-
0.9929	280	0.0751	-
1.0	282	-	0.6395
1.0284	290	0.166	-
1.0638	300	0.0842	-
1.0993	310	0.098	-
1.1348	320	0.0674	-
1.1702	330	0.071	-
1.2057	340	0.0527	-
1.2411	350	0.0401	-
1.2766	360	0.0575	-
1.3121	370	0.0418	-
1.3475	380	0.054	-
1.3830	390	0.0495	-
1.4184	400	0.0355	-
1.4539	410	0.0449	-
1.4894	420	0.0509	-
1.5248	430	0.0196	-
1.5603	440	0.0634	-
1.5957	450	0.0522	-
1.6312	460	0.0477	-
1.6667	470	0.0583	-
1.7021	480	0.0584	-
1.7376	490	0.0553	-
1.7730	500	0.0358	-
1.8085	510	0.0253	-
1.8440	520	0.0541	-
1.8794	530	0.0488	-
1.9149	540	0.0528	-
1.9504	550	0.0474	-
1.9858	560	0.0311	-
2.0	564	-	0.6384

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.14
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2+cu121
Accelerate: 0.32.1
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}
}