Graft combines pruning and retrieval in a sequential mechanism to build hybrid draft trees for speculative decoding, delivering up to 5.41× speedup and 21.8% better average speedup than EAGLE-3 on large models.
hub
Abstractive text summarization using sequence-to-sequence RNN s and beyond
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
abstract
In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora. We propose several novel models that address critical problems in summarization that are not adequately modeled by the basic architecture, such as modeling key-words, capturing the hierarchy of sentence-to-word structure, and emitting words that are rare or unseen at training time. Our work shows that many of our proposed models contribute to further improvement in performance. We also propose a new dataset consisting of multi-sentence summaries, and establish performance benchmarks for further research.
hub tools
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
An identification theorem shows that a randomized experiment and simulator together recover causal model values from confounded logs, with logs used only afterward to reduce estimation error.
A McNemar-based statistical test detects real degradations in optimized LLMs with controlled false positives, even for accuracy changes as small as 0.3%.
H2O evicts non-heavy-hitter tokens from the KV cache using a dynamic submodular policy, retaining recent and frequent-co-occurrence tokens to reduce memory while preserving accuracy.
CTRL is a large conditional transformer language model that uses naturally occurring control codes to steer text generation style and content.
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.
A score-ranking loss enables controllable summarization by aligning outputs to evaluation scores, matching SOTA performance with dimension-specific control on LLaMA, Qwen, and Mistral.
Two RL-based extractive summarization models rank sentences from product fields by leveraging titles and click-through logs to improve search relevance.
LRP saliency maps on a seq2seq summarization model sometimes reflect actual input feature usage and sometimes do not, requiring quantitative counterfactual validation.
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.
citing papers explorer
-
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Graft combines pruning and retrieval in a sequential mechanism to build hybrid draft trees for speculative decoding, delivering up to 5.41× speedup and 21.8% better average speedup than EAGLE-3 on large models.
-
The Partial Testimony of Logs: Evaluation of Language Model Generation under Confounded Model Choice
An identification theorem shows that a randomized experiment and simulator together recover causal model values from confounded logs, with logs used only afterward to reduce estimation error.
-
When LLMs get significantly worse: A statistical approach to detect model degradations
A McNemar-based statistical test detects real degradations in optimized LLMs with controlled false positives, even for accuracy changes as small as 0.3%.
-
H$_2$O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models
H2O evicts non-heavy-hitter tokens from the KV cache using a dynamic submodular policy, retaining recent and frequent-co-occurrence tokens to reduce memory while preserving accuracy.
-
CTRL: A Conditional Transformer Language Model for Controllable Generation
CTRL is a large conditional transformer language model that uses naturally occurring control codes to steer text generation style and content.
-
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
A proposed pipeline shows LLMs introduce detectable race and gender biases when summarizing life narratives, creating potential for representational harm in research.
-
Reasoning Structure Matters for Safety Alignment of Reasoning Models
Changing the internal reasoning structure of large reasoning models through simple supervised fine-tuning on 1K examples produces strong safety alignment that generalizes across tasks and languages.
-
Learning to Control Summaries with Score Ranking
A score-ranking loss enables controllable summarization by aligning outputs to evaluation scores, matching SOTA performance with dimension-specific control on LLaMA, Qwen, and Mistral.
-
Ranking sentences from product description & bullets for better search
Two RL-based extractive summarization models rank sentences from product fields by leveraging titles and click-through logs to improve search relevance.
-
Saliency Maps Generation for Automatic Text Summarization
LRP saliency maps on a seq2seq summarization model sometimes reflect actual input feature usage and sometimes do not, requiring quantitative counterfactual validation.
-
Large Language Models: A Survey
The paper surveys key large language models, their training methods, datasets, evaluation benchmarks, and future research directions in the field.
-
Bias in Large Language Models: Origin, Evaluation, and Mitigation
A literature review that categorizes bias in LLMs, surveys evaluation and mitigation techniques, and discusses ethical implications.