Generating Intermediate Steps for NLI with Next-Step Supervision

• URL: http://arxiv.org/abs/2208.14641v1
• Date: Wed, 31 Aug 2022 05:25:33 GMT
• Title: Generating Intermediate Steps for NLI with Next-Step Supervision
• Authors: Deepanway Ghosal and Somak Aditya and Monojit Choudhury
• Abstract summary: We train a sequence-to-sequence model to generate only the next step given an NLI premise and hypothesis pair. We then enhance it with external knowledge and symbolic search to generate intermediate steps with only next-step supervision. We show the correctness of such generated steps through automated and human verification.
• Score: 15.425765421938447
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The Natural Language Inference (NLI) task often requires reasoning over multiple steps to reach the conclusion. While the necessity of generating such intermediate steps (instead of a summary explanation) has gained popular support, it is unclear how to generate such steps without complete end-to-end supervision and how such generated steps can be further utilized. In this work, we train a sequence-to-sequence model to generate only the next step given an NLI premise and hypothesis pair (and previous steps); then enhance it with external knowledge and symbolic search to generate intermediate steps with only next-step supervision. We show the correctness of such generated steps through automated and human verification. Furthermore, we show that such generated steps can help improve end-to-end NLI task performance using simple data augmentation strategies, across multiple public NLI datasets.

Related papers

• RLAP: A Reinforcement Learning Enhanced Adaptive Planning Framework for Multi-step NLP Task Solving [14.11486479935094]
  Multi-step planning has been widely employed to enhance the performance of large language models (LLMs) on downstream natural language processing (NLP) tasks.<n>We propose a Reinforcement Learning enhanced Adaptive Planning framework (RLAP) to better solve multi-step NLP tasks.
  arXiv  Detail & Related papers  (2025-05-17T08:06:14Z)
• Stepwise Informativeness Search for Efficient and Effective LLM Reasoning [49.85349030928302]
  Recent studies show that Large Language Models (LLMs) tend to lose focus over the middle of long contexts. We propose guiding LLMs to generate more accurate and concise step-by-step rationales.
  arXiv  Detail & Related papers  (2025-02-21T09:39:27Z)
• Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation [34.55224347308013]
  Traditional supervised fine-tuning (SFT) strategies for sequence-to-sequence tasks often train models to directly generate the target output. We introduce a task-agnostic framework that enables models to generate intermediate "upwarm" sequences. We show that our approach outperforms traditional SFT methods, and offers a scalable and flexible solution for sequence-to-sequence tasks.
  arXiv  Detail & Related papers  (2025-02-17T20:23:42Z)
• Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models [93.5327725085853]
  Continual LLaVA is a rehearsal-free method tailored for continual instruction tuning in LVLMs. Experiments indicate that the proposed Continual LLaVA outperforms previous methods by significantly reducing the forgetting during the continual instruction tuning process.
  arXiv  Detail & Related papers  (2024-11-04T19:55:32Z)
• Write Summary Step-by-Step: A Pilot Study of Stepwise Summarization [48.57273563299046]
  We propose the task of Stepwise Summarization, which aims to generate a new appended summary each time a new document is proposed. The appended summary should not only summarize the newly added content but also be coherent with the previous summary. We show that SSG achieves state-of-the-art performance in terms of both automatic metrics and human evaluations.
  arXiv  Detail & Related papers  (2024-06-08T05:37:26Z)
• A Simple Finite-Time Analysis of TD Learning with Linear Function Approximation [2.44755919161855]
  We study the finite-time convergence of TD learning with linear function approximation under Markovian sampling. We show that it is possible to retain the simplicity of a projection-based analysis without actually performing a projection step in the algorithm.
  arXiv  Detail & Related papers  (2024-03-04T20:40:02Z)
• Prompt Sketching for Large Language Models [7.687678490751105]
  Recent prompting strategies for large language models (LLMs) query the model multiple times sequentially. This leads to disconnected and undesirably wordy intermediate responses. We propose prompt sketching, a new prompting paradigm in which an LLM does not only respond by completing a prompt, but by predicting values for multiple variables in a template.
  arXiv  Detail & Related papers  (2023-11-08T18:57:23Z)
• Guiding Language Model Reasoning with Planning Tokens [122.43639723387516]
  Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks. We propose a hierarchical generation scheme to encourage a more structural generation of chain-of-thought steps. Our approach requires a negligible increase in trainable parameters (0.001%) and can be applied through either full fine-tuning or a more parameter-efficient scheme.
  arXiv  Detail & Related papers  (2023-10-09T13:29:37Z)
• Non-Sequential Graph Script Induction via Multimedia Grounding [129.83134296316493]
  We train a script knowledge model capable of both generating explicit graph scripts for learnt tasks and predicting future steps given a partial step sequence. Human evaluation shows our model outperforming the WikiHow linear baseline by 48.76% absolute gains in capturing sequential and non-sequential step relationships.
  arXiv  Detail & Related papers  (2023-05-27T18:13:17Z)
• Planning with Sequence Models through Iterative Energy Minimization [22.594413287842574]
  We suggest an approach towards integrating planning with sequence models based on the idea of iterative energy minimization. We train a masked language model to capture an implicit energy function over trajectories of actions, and formulate planning as finding a trajectory of actions with minimum energy. We illustrate how this procedure enables improved performance over recent approaches across BabyAI and Atari environments.
  arXiv  Detail & Related papers  (2023-03-28T17:53:22Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• SVIP: Sequence VerIfication for Procedures in Videos [68.07865790764237]
  We propose a novel sequence verification task that aims to distinguish positive video pairs performing the same action sequence from negative ones with step-level transformations. Such a challenging task resides in an open-set setting without prior action detection or segmentation. We collect a scripted video dataset enumerating all kinds of step-level transformations in chemical experiments.
  arXiv  Detail & Related papers  (2021-12-13T07:03:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.