abstracts sequencelengths 2 2 | id_1 stringlengths 9 14 | id_2 stringlengths 9 14 | pair_id stringlengths 20 25 | joint_prompt stringlengths 687 3.9k | paper1_prompt stringlengths 212 1.94k | paper2_prompt stringlengths 212 1.94k | no_context_prompt stringclasses 1
value | data_source stringclasses 1
value | prompt listlengths 1 1 | ability stringclasses 1
value | reward_model dict | extra_info dict | prompt_tok_length int64 270 1.04k |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
[
" False news that spreads on social media has proliferated over the past years\nand has led to multi-aspect threats in the real world. While there are studies\nof false news on specific domains (like politics or health care), little work\nis found comparing false news across domains. In this article, we investigat... | 2205.03068 | 2203.08304 | 2205.03068_2203.08304 | Paper 1:
False news that spreads on social media has proliferated over the past years
and has led to multi-aspect threats in the real world. While there are studies
of false news on specific domains (like politics or health care), little work
is found comparing false news across domains. In this article, we investigate... | Paper:
False news that spreads on social media has proliferated over the past years
and has led to multi-aspect threats in the real world. While there are studies
of false news on specific domains (like politics or health care), little work
is found comparing false news across domains. In this article, we investigate
f... | Paper:
We investigate input-conditioned hypernetworks for multi-tasking in NLP,
generating parameter-efficient adaptations for a decoder using a hypernetwork
conditioned on the output of an encoder. This approach produces a unique
decoder adaptation for every input instance, allowing the network a larger
degree of flex... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" False news that spreads on social media has proliferated over the past years\nand has led to multi-aspect threats in the real world. While there are studies\nof false news on specific domains (like politics or health care), little work\nis found comparing false news across domains. In this art... | 672 | |
[
" End-to-end speech-to-text translation models are often initialized with\npre-trained speech encoder and pre-trained text decoder. This leads to a\nsignificant training gap between pre-training and fine-tuning, largely due to\nthe modality differences between speech outputs from the encoder and text\ninputs to th... | 2207.00952 | 2205.13621 | 2207.00952_2205.13621 | Paper 1:
End-to-end speech-to-text translation models are often initialized with
pre-trained speech encoder and pre-trained text decoder. This leads to a
significant training gap between pre-training and fine-tuning, largely due to
the modality differences between speech outputs from the encoder and text
inputs to the ... | Paper:
End-to-end speech-to-text translation models are often initialized with
pre-trained speech encoder and pre-trained text decoder. This leads to a
significant training gap between pre-training and fine-tuning, largely due to
the modality differences between speech outputs from the encoder and text
inputs to the de... | Paper:
Recent large-scale natural language processing (NLP) systems use a
pre-trained Large Language Model (LLM) on massive and diverse corpora as a
headstart. In practice, the pre-trained model is adapted to a wide array of
tasks via fine-tuning on task-specific datasets. LLMs, while effective, have
been shown to memo... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" End-to-end speech-to-text translation models are often initialized with\npre-trained speech encoder and pre-trained text decoder. This leads to a\nsignificant training gap between pre-training and fine-tuning, largely due to\nthe modality differences between speech outputs from the encoder and... | 554 | |
[
" Visual dialog is challenging since it needs to answer a series of coherent\nquestions based on understanding the visual environment. How to ground related\nvisual objects is one of the key problems. Previous studies utilize the\nquestion and history to attend to the image and achieve satisfactory\nperformance, h... | 2109.06013 | 2106.12144 | 2109.06013_2106.12144 | Paper 1:
Visual dialog is challenging since it needs to answer a series of coherent
questions based on understanding the visual environment. How to ground related
visual objects is one of the key problems. Previous studies utilize the
question and history to attend to the image and achieve satisfactory
performance, how... | Paper:
Visual dialog is challenging since it needs to answer a series of coherent
questions based on understanding the visual environment. How to ground related
visual objects is one of the key problems. Previous studies utilize the
question and history to attend to the image and achieve satisfactory
performance, howev... | Paper:
Conventional representation learning algorithms for knowledge graphs (KG) map
each entity to a unique embedding vector. Such a shallow lookup results in a
linear growth of memory consumption for storing the embedding matrix and incurs
high computational costs when working with real-world KGs. Drawing parallels
w... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" Visual dialog is challenging since it needs to answer a series of coherent\nquestions based on understanding the visual environment. How to ground related\nvisual objects is one of the key problems. Previous studies utilize the\nquestion and history to attend to the image and achieve satisfact... | 648 | |
[
" Logical Table-to-Text (LT2T) generation is tasked with generating logically\nfaithful sentences from tables. There currently exists two challenges in the\nfield: 1) Faithfulness: how to generate sentences that are factually correct\ngiven the table content; 2) Diversity: how to generate multiple sentences that\n... | 2302.02962 | 2203.00249 | 2302.02962_2203.00249 | Paper 1:
Logical Table-to-Text (LT2T) generation is tasked with generating logically
faithful sentences from tables. There currently exists two challenges in the
field: 1) Faithfulness: how to generate sentences that are factually correct
given the table content; 2) Diversity: how to generate multiple sentences that
of... | Paper:
Logical Table-to-Text (LT2T) generation is tasked with generating logically
faithful sentences from tables. There currently exists two challenges in the
field: 1) Faithfulness: how to generate sentences that are factually correct
given the table content; 2) Diversity: how to generate multiple sentences that
offe... | Paper:
While GPT has become the de-facto method for text generation tasks, its
application to pinyin input method remains unexplored. In this work, we make
the first exploration to leverage Chinese GPT for pinyin input method. We find
that a frozen GPT achieves state-of-the-art performance on perfect pinyin.
However, t... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" Logical Table-to-Text (LT2T) generation is tasked with generating logically\nfaithful sentences from tables. There currently exists two challenges in the\nfield: 1) Faithfulness: how to generate sentences that are factually correct\ngiven the table content; 2) Diversity: how to generate multip... | 497 | |
[
" We present a novel feature attribution method for explaining text\nclassifiers, and analyze it in the context of hate speech detection. Although\nfeature attribution models usually provide a single importance score for each\ntoken, we instead provide two complementary and theoretically-grounded scores\n-- necess... | 2205.03302 | 2302.12578 | 2205.03302_2302.12578 | Paper 1:
We present a novel feature attribution method for explaining text
classifiers, and analyze it in the context of hate speech detection. Although
feature attribution models usually provide a single importance score for each
token, we instead provide two complementary and theoretically-grounded scores
-- necessit... | Paper:
We present a novel feature attribution method for explaining text
classifiers, and analyze it in the context of hate speech detection. Although
feature attribution models usually provide a single importance score for each
token, we instead provide two complementary and theoretically-grounded scores
-- necessity ... | Paper:
With language models becoming increasingly ubiquitous, it has become
essential to address their inequitable treatment of diverse demographic groups
and factors. Most research on evaluating and mitigating fairness harms has been
concentrated on English, while multilingual models and non-English languages
have rec... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" We present a novel feature attribution method for explaining text\nclassifiers, and analyze it in the context of hate speech detection. Although\nfeature attribution models usually provide a single importance score for each\ntoken, we instead provide two complementary and theoretically-grounde... | 470 | |
[
" Morality in dialogue systems has raised great attention in research recently.\nA moral dialogue system aligned with users' values could enhance conversation\nengagement and user connections. In this paper, we propose a framework,\nMoralDial to train and evaluate moral dialogue systems. In our framework, we\nfirs... | 2212.10720 | 2211.01910 | 2212.10720_2211.01910 | Paper 1:
Morality in dialogue systems has raised great attention in research recently.
A moral dialogue system aligned with users' values could enhance conversation
engagement and user connections. In this paper, we propose a framework,
MoralDial to train and evaluate moral dialogue systems. In our framework, we
first ... | Paper:
Morality in dialogue systems has raised great attention in research recently.
A moral dialogue system aligned with users' values could enhance conversation
engagement and user connections. In this paper, we propose a framework,
MoralDial to train and evaluate moral dialogue systems. In our framework, we
first ex... | Paper:
By conditioning on natural language instructions, large language models
(LLMs) have displayed impressive capabilities as general-purpose computers.
However, task performance depends significantly on the quality of the prompt
used to steer the model, and most effective prompts have been handcrafted by
humans. Ins... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" Morality in dialogue systems has raised great attention in research recently.\nA moral dialogue system aligned with users' values could enhance conversation\nengagement and user connections. In this paper, we propose a framework,\nMoralDial to train and evaluate moral dialogue systems. In our ... | 641 | |
[
" ChatGPT and Bard are AI chatbots based on Large Language Models (LLM) that\nare slated to promise different applications in diverse areas. In education,\nthese AI technologies have been tested for applications in assessment and\nteaching. In assessment, AI has long been used in automated essay scoring and\nautom... | 2304.05372 | 2306.16650 | 2304.05372_2306.16650 | Paper 1:
ChatGPT and Bard are AI chatbots based on Large Language Models (LLM) that
are slated to promise different applications in diverse areas. In education,
these AI technologies have been tested for applications in assessment and
teaching. In assessment, AI has long been used in automated essay scoring and
automat... | Paper:
ChatGPT and Bard are AI chatbots based on Large Language Models (LLM) that
are slated to promise different applications in diverse areas. In education,
these AI technologies have been tested for applications in assessment and
teaching. In assessment, AI has long been used in automated essay scoring and
automated... | Paper:
Multimodal Sarcasm Explanation (MuSE) is a new yet challenging task, which
aims to generate a natural language sentence for a multimodal social post (an
image as well as its caption) to explain why it contains sarcasm. Although the
existing pioneer study has achieved great success with the BART backbone, it
over... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" ChatGPT and Bard are AI chatbots based on Large Language Models (LLM) that\nare slated to promise different applications in diverse areas. In education,\nthese AI technologies have been tested for applications in assessment and\nteaching. In assessment, AI has long been used in automated essay... | 570 | |
[
" Retrieval augmentation can aid language models (LMs) in knowledge-intensive\ntasks by supplying them with external information. Prior works on retrieval\naugmentation usually jointly fine-tune the retriever and the LM, making them\nclosely coupled. In this paper, we explore the scheme of generic retrieval\nplug-... | 2305.17331 | 2210.04982 | 2305.17331_2210.04982 | Paper 1:
Retrieval augmentation can aid language models (LMs) in knowledge-intensive
tasks by supplying them with external information. Prior works on retrieval
augmentation usually jointly fine-tune the retriever and the LM, making them
closely coupled. In this paper, we explore the scheme of generic retrieval
plug-in... | Paper:
Retrieval augmentation can aid language models (LMs) in knowledge-intensive
tasks by supplying them with external information. Prior works on retrieval
augmentation usually jointly fine-tune the retriever and the LM, making them
closely coupled. In this paper, we explore the scheme of generic retrieval
plug-in: ... | Paper:
Generating free-text rationales is a promising step towards explainable NLP,
yet evaluating such rationales remains a challenge. Existing metrics have
mostly focused on measuring the association between the rationale and a given
label. We argue that an ideal metric should focus on the new information
uniquely pr... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" Retrieval augmentation can aid language models (LMs) in knowledge-intensive\ntasks by supplying them with external information. Prior works on retrieval\naugmentation usually jointly fine-tune the retriever and the LM, making them\nclosely coupled. In this paper, we explore the scheme of gener... | 628 | |
[
" Video captioning aims to generate natural language sentences that describe\nthe given video accurately. Existing methods obtain favorable generation by\nexploring richer visual representations in encode phase or improving the\ndecoding ability. However, the long-tailed problem hinders these attempts at\nlow-freq... | 2211.15076 | 2303.02513 | 2211.15076_2303.02513 | Paper 1:
Video captioning aims to generate natural language sentences that describe
the given video accurately. Existing methods obtain favorable generation by
exploring richer visual representations in encode phase or improving the
decoding ability. However, the long-tailed problem hinders these attempts at
low-freque... | Paper:
Video captioning aims to generate natural language sentences that describe
the given video accurately. Existing methods obtain favorable generation by
exploring richer visual representations in encode phase or improving the
decoding ability. However, the long-tailed problem hinders these attempts at
low-frequenc... | Paper:
Hate speech in social media is a growing phenomenon, and detecting such toxic
content has recently gained significant traction in the research community.
Existing studies have explored fine-tuning language models (LMs) to perform
hate speech detection, and these solutions have yielded significant
performance. Ho... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" Video captioning aims to generate natural language sentences that describe\nthe given video accurately. Existing methods obtain favorable generation by\nexploring richer visual representations in encode phase or improving the\ndecoding ability. However, the long-tailed problem hinders these at... | 707 | |
[
" A fundamental goal of scientific research is to learn about causal\nrelationships. However, despite its critical role in the life and social\nsciences, causality has not had the same importance in Natural Language\nProcessing (NLP), which has traditionally placed more emphasis on predictive\ntasks. This distinct... | 2109.00725 | 2111.03777 | 2109.00725_2111.03777 | Paper 1:
A fundamental goal of scientific research is to learn about causal
relationships. However, despite its critical role in the life and social
sciences, causality has not had the same importance in Natural Language
Processing (NLP), which has traditionally placed more emphasis on predictive
tasks. This distinctio... | Paper:
A fundamental goal of scientific research is to learn about causal
relationships. However, despite its critical role in the life and social
sciences, causality has not had the same importance in Natural Language
Processing (NLP), which has traditionally placed more emphasis on predictive
tasks. This distinction ... | Paper:
This paper investigates methods to effectively retrieve speaker information
from the personalized speaker adapted neural network acoustic models (AMs) in
automatic speech recognition (ASR). This problem is especially important in the
context of federated learning of ASR acoustic models where a global model is
le... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" A fundamental goal of scientific research is to learn about causal\nrelationships. However, despite its critical role in the life and social\nsciences, causality has not had the same importance in Natural Language\nProcessing (NLP), which has traditionally placed more emphasis on predictive\nt... | 532 | |
[
" Many open-domain dialogue models pre-trained with social media comments can\ngenerate coherent replies but have difficulties producing engaging responses\nwhen interacting with real users. This phenomenon might mainly result from the\ndeficiency of annotated human-human conversations and the misalignment with\nh... | 2208.14165 | 2203.12186 | 2208.14165_2203.12186 | Paper 1:
Many open-domain dialogue models pre-trained with social media comments can
generate coherent replies but have difficulties producing engaging responses
when interacting with real users. This phenomenon might mainly result from the
deficiency of annotated human-human conversations and the misalignment with
hum... | Paper:
Many open-domain dialogue models pre-trained with social media comments can
generate coherent replies but have difficulties producing engaging responses
when interacting with real users. This phenomenon might mainly result from the
deficiency of annotated human-human conversations and the misalignment with
human... | Paper:
Transformers have recently been shown to be capable of reliably performing
logical reasoning over facts and rules expressed in natural language, but
abductive reasoning - inference to the best explanation of an unexpected
observation - has been underexplored despite significant applications to
scientific discove... | Here's an insight: | [
{
"content": "<|im_start|>user\nYou are a helpful AI Assistant that provides well-reasoned and detailed responses. Identify an insight that emerges only when both papers are considered together—something not obvious from either paper alone. You first think about the reasoning process as an internal monologue (1... | insight | {
"ground_truth": "",
"style": "rule"
} | {
"abstracts": [
" Many open-domain dialogue models pre-trained with social media comments can\ngenerate coherent replies but have difficulties producing engaging responses\nwhen interacting with real users. This phenomenon might mainly result from the\ndeficiency of annotated human-human conversations and the m... | 488 |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 6