Parag Jain

Laura Perez-Beltrachini, Parag Jain, Emilio Monti et al. · amazon-science

In this paper, we are interested in developing semantic parsers which understand natural language questions embedded in a conversation with a user and ground them to formal queries over definitions in a general purpose knowledge graph (KG) with very large vocabularies (covering thousands of concept names and relations, and millions of entities). To this end, we develop a dataset where user questions are annotated with Sparql parses and system answers correspond to execution results thereof. We present two different semantic parsing approaches and highlight the challenges of the task: dealing with large vocabularies, modelling conversation context, predicting queries with multiple entities, and generalising to new questions at test time. We hope our dataset will serve as useful testbed for the development of conversational semantic parsers. Our dataset and models are released at https://github.com/EdinburghNLP/SPICE.

Ratish Puduppully, Parag Jain, Nancy F. Chen et al.

In Multi-Document Summarization (MDS), the input can be modeled as a set of documents, and the output is its summary. In this paper, we focus on pretraining objectives for MDS. Specifically, we introduce a novel pretraining objective, which involves selecting the ROUGE-based centroid of each document cluster as a proxy for its summary. Our objective thus does not require human written summaries and can be utilized for pretraining on a dataset consisting solely of document sets. Through zero-shot, few-shot, and fully supervised experiments on multiple MDS datasets, we show that our model Centrum is better or comparable to a state-of-the-art model. We make the pretrained and fine-tuned models freely available to the research community https://github.com/ratishsp/centrum.

Shashwat Goel, Rishi Hazra, Dulhan Jayalath et al.

AI co-scientists are emerging as a tool to assist human researchers in achieving their research goals. A crucial feature of these AI co-scientists is the ability to generate a research plan given a set of aims and constraints. The plan may be used by researchers for brainstorming, or may even be implemented after further refinement. However, language models currently struggle to generate research plans that follow all constraints and implicit requirements. In this work, we study how to leverage the vast corpus of existing research papers to train language models that generate better research plans. We build a scalable, diverse training corpus by automatically extracting research goals and goal-specific grading rubrics from papers across several domains. We then train models for research plan generation via reinforcement learning with self-grading. A frozen copy of the initial policy acts as the grader during training, with the rubrics creating a generator-verifier gap that enables improvements without external human supervision. To validate this approach, we conduct a study with human experts for machine learning research goals, spanning 225 hours. The experts prefer plans generated by our finetuned Qwen3-30B-A3B model over the initial model for 70% of research goals, and approve 84% of the automatically extracted goal-specific grading rubrics. To assess generality, we also extend our approach to research goals from medical papers, and new arXiv preprints, evaluating with a jury of frontier models. Our finetuning yields 12-22% relative improvements and significant cross-domain generalization, proving effective even in problem settings like medical research where execution feedback is infeasible. Together, these findings demonstrate the potential of a scalable, automated training recipe as a step towards improving general AI co-scientists.

Parag Jain, Andreea Marzoca, Francesco Piccinno

We consider the task of generating structured representations of text using large language models (LLMs). We focus on tables and mind maps as representative modalities. Tables are more organized way of representing data, while mind maps provide a visually dynamic and flexible approach, particularly suitable for sparse content. Despite the effectiveness of LLMs on different tasks, we show that current models struggle with generating structured outputs. In response, we present effective prompting strategies for both of these tasks. We introduce a taxonomy of problems around factuality, global and local structure, common to both modalities and propose a set of critiques to tackle these issues resulting in an absolute improvement in accuracy of +37pp (79%) for mind maps and +15pp (78%) for tables. To evaluate semantic coverage of generated structured representations we propose Auto-QA, and we verify the adequacy of Auto-QA using SQuAD dataset. We further evaluate the usefulness of structured representations via a text comprehension user study. The results show a significant reduction in comprehension time compared to text when using table (42.9%) and mind map (31.9%), without loss in accuracy.

Dulhan Jayalath, Shashwat Goel, Thomas Foster et al. · allen-ai

Where do learning signals come from when there is no ground truth in post-training? We propose turning exploration into supervision through Compute as Teacher (CaT), which converts the model's own exploration at inference-time into reference-free supervision by synthesizing a single reference from a group of parallel rollouts and then optimizing toward it. Concretely, the current policy produces a group of rollouts; a frozen anchor (the initial policy) reconciles omissions and contradictions to estimate a reference, turning extra inference-time compute into a teacher signal. We turn this into rewards in two regimes: (i) verifiable tasks use programmatic equivalence on final answers; (ii) non-verifiable tasks use self-proposed rubrics-binary, auditable criteria scored by an independent LLM judge, with reward given by the fraction satisfied. Unlike selection methods (best-of-N, majority, perplexity, or judge scores), synthesis may disagree with the majority and be correct even when all rollouts are wrong; performance scales with the number of rollouts. As a test-time procedure, CaT improves Gemma 3 4B, Qwen 3 4B, and Llama 3.1 8B (up to +27% on MATH-500; +12% on HealthBench). With reinforcement learning (CaT-RL), we obtain further gains (up to +33% and +30%), with the trained policy surpassing the initial teacher signal.

Yunzhen Feng, Julia Kempe, Cheng Zhang et al. · pku

Large reasoning models (LRMs) spend substantial test-time compute on long chain-of-thought (CoT) traces, but what *characterizes* an effective CoT remains unclear. While prior work reports gains from lengthening CoTs and increasing review (revisiting earlier steps) via appended *wait* tokens, recent studies suggest that shorter thinking can outperform longer traces. We therefore conduct a systematic evaluation across ten LRMs on math and scientific reasoning. Contrary to the "longer-is-better" narrative, we find that both naive CoT lengthening and increased review are associated with *lower* accuracy. As CoT unfolds step by step, token-level metrics can conflate verbosity with process quality. We introduce a graph view of CoT to extract structure and identify a single statistic-the *Failed-Step Fraction (FSF)*, the fraction of steps in abandoned branches-that consistently outpredicts length and review ratio for correctness across models. To probe causality, we design two interventions. First, we rank candidate CoTs by each metric at test time, where FSF yields the largest pass@1 gains; second, we edit CoTs to remove failed branches, which significantly improves accuracy, indicating that failed branches bias subsequent reasoning. Taken together, these results characterize effective CoTs as those that *fail less* and support *structure-aware* test-time scaling over indiscriminately generating long CoT.

Yunzhen Feng, Parag Jain, Anthony Hartshorn et al. · pku

Reinforcement learning with verifiable rewards (RLVR) has become a standard recipe for improving large language models (LLMs) on reasoning tasks, with Group Relative Policy Optimization (GRPO) widely used in practice. Yet GRPO wastes substantial compute on negative groups: groups in which no sampled response is correct yield zero advantage and thus no gradient. We ask whether negative groups can be leveraged without extra supervision. Starting from a maximum-likelihood (MLE) objective in reward modeling, we show that the MLE gradient is equivalent to a policy gradient for a modified value function. This value function adds a confidence-weighted penalty on incorrect responses, imposing larger penalties on more confident mistakes. We refer to this as \textbf{L}ikelihood \textbf{E}stimation with \textbf{N}egative \textbf{S}amples (\textbf{LENS}). LENS modifies GRPO to assign non-zero, confidence-dependent rewards to incorrect generations, making negative groups informative and converting previously wasted samples into useful gradient updates. On the MATH benchmark with Llama-3.1-8B and Qwen-2.5-3B, the proposed variant consistently outperforms GRPO baseline, with significant gains on harder items. These results demonstrate a principled and practical way to "rescue" negative groups, improving efficiency and performance in RLVR.

Parag Jain, Mirella Lapata

We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from heterogeneous sources like text, knowledge graphs, tables, and infoboxes. Our method utilizes a graph structured representation to aggregate information about a question and its context (i.e., the conversation so far and evidence retrieved to find an answer), while also harnessing the reasoning and text generation capabilities of large language models (LLMs). Graph embeddings are directly injected into the LLM, bypassing the token embedding layers, and learned end-to-end by minimizing cross-entropy. Our model maintains a memory module to track and update past evidence, thus influencing the graph's structure, as the conversation evolves. Experimental results on the ConvMix benchmark(Christmann et al., 2022a) show that graph embeddings enhance the LLM's ability to reason, while the memory module provides robustness against noise and retrieval errors.

Parag Jain, Mirella Lapata

In this paper we consider the task of conversational semantic parsing over general purpose knowledge graphs (KGs) with millions of entities, and thousands of relation-types. We focus on models which are capable of interactively mapping user utterances into executable logical forms (e.g., Sparql) in the context of the conversational history. Our key idea is to represent information about an utterance and its context via a subgraph which is created dynamically, i.e., the number of nodes varies per utterance. Rather than treating the subgraph as a sequence, we exploit its underlying structure and encode it with a graph neural network which further allows us to represent a large number of (unseen) nodes. Experimental results show that dynamic context modeling is superior to static approaches, delivering performance improvements across the board (i.e., for simple and complex questions). Our results further confirm that modeling the structure of context is better at processing discourse information, (i.e., at handling ellipsis and resolving coreference) and longer interactions.

Parag Jain, Mirella Lapata

We present a memory-based model for context-dependent semantic parsing. Previous approaches focus on enabling the decoder to copy or modify the parse from the previous utterance, assuming there is a dependency between the current and previous parses. In this work, we propose to represent contextual information using an external memory. We learn a context memory controller that manages the memory by maintaining the cumulative meaning of sequential user utterances. We evaluate our approach on three semantic parsing benchmarks. Experimental results show that our model can better process context-dependent information and demonstrates improved performance without using task-specific decoders.

Priyanka Agrawal, Parag Jain, Ayushi Dalmia et al.

Semantic parsing over multiple knowledge bases enables a parser to exploit structural similarities of programs across the multiple domains. However, the fundamental challenge lies in obtaining high-quality annotations of (utterance, program) pairs across various domains needed for training such models. To overcome this, we propose a novel framework to build a unified multi-domain enabled semantic parser trained only with weak supervision (denotations). Weakly supervised training is particularly arduous as the program search space grows exponentially in a multi-domain setting. To solve this, we incorporate a multi-policy distillation mechanism in which we first train domain-specific semantic parsers (teachers) using weak supervision in the absence of the ground truth programs, followed by training a single unified parser (student) from the domain specific policies obtained from these teachers. The resultant semantic parser is not only compact but also generalizes better, and generates more accurate programs. It further does not require the user to provide a domain label while querying. On the standard Overnight dataset (containing multiple domains), we demonstrate that the proposed model improves performance by 20% in terms of denotation accuracy in comparison to baseline techniques.

Sai Surya, Abhijit Mishra, Anirban Laha et al.

The paper presents a first attempt towards unsupervised neural text simplification that relies only on unlabeled text corpora. The core framework is composed of a shared encoder and a pair of attentional-decoders and gains knowledge of simplification through discrimination based-losses and denoising. The framework is trained using unlabeled text collected from en-Wikipedia dump. Our analysis (both quantitative and qualitative involving human evaluators) on a public test data shows that the proposed model can perform text-simplification at both lexical and syntactic levels, competitive to existing supervised methods. Addition of a few labelled pairs also improves the performance further.

Anirban Laha, Parag Jain, Abhijit Mishra et al.

We present a framework for generating natural language description from structured data such as tables; the problem comes under the category of data-to-text natural language generation (NLG). Modern data-to-text NLG systems typically employ end-to-end statistical and neural architectures that learn from a limited amount of task-specific labeled data, and therefore, exhibit limited scalability, domain-adaptability, and interpretability. Unlike these systems, ours is a modular, pipeline-based approach, and does not require task-specific parallel data. It rather relies on monolingual corpora and basic off-the-shelf NLP tools. This makes our system more scalable and easily adaptable to newer domains. Our system employs a 3-staged pipeline that: (i) converts entries in the structured data to canonical form, (ii) generates simple sentences for each atomic entry in the canonicalized representation, and (iii) combines the sentences to produce a coherent, fluent and adequate paragraph description through sentence compounding and co-reference replacement modules. Experiments on a benchmark mixed-domain dataset curated for paragraph description from tables reveals the superiority of our system over existing data-to-text approaches. We also demonstrate the robustness of our system in accepting other popular datasets covering diverse data types such as Knowledge Graphs and Key-Value maps.

Parag Jain, Abhijit Mishra, Amar Prakash Azad et al.

We propose a novel framework for controllable natural language transformation. Realizing that the requirement of parallel corpus is practically unsustainable for controllable generation tasks, an unsupervised training scheme is introduced. The crux of the framework is a deep neural encoder-decoder that is reinforced with text-transformation knowledge through auxiliary modules (called scorers). The scorers, based on off-the-shelf language processing tools, decide the learning scheme of the encoder-decoder based on its actions. We apply this framework for the text-transformation task of formalizing an input text by improving its readability grade; the degree of required formalization can be controlled by the user at run-time. Experiments on public datasets demonstrate the efficacy of our model towards: (a) transforming a given text to a more formal style, and (b) introducing appropriate amount of formalness in the output text pertaining to the input control. Our code and datasets are released for academic use.

Parag Jain, Anirban Laha, Karthik Sankaranarayanan et al.

Structured data summarization involves generation of natural language summaries from structured input data. In this work, we consider summarizing structured data occurring in the form of tables as they are prevalent across a wide variety of domains. We formulate the standard table summarization problem, which deals with tables conforming to a single predefined schema. To this end, we propose a mixed hierarchical attention based encoder-decoder model which is able to leverage the structure in addition to the content of the tables. Our experiments on the publicly available WEATHERGOV dataset show around 18 BLEU (~ 30%) improvement over the current state-of-the-art.

Preksha Nema, Shreyas Shetty, Parag Jain et al.

In this work, we focus on the task of generating natural language descriptions from a structured table of facts containing fields (such as nationality, occupation, etc) and values (such as Indian, actor, director, etc). One simple choice is to treat the table as a sequence of fields and values and then use a standard seq2seq model for this task. However, such a model is too generic and does not exploit task-specific characteristics. For example, while generating descriptions from a table, a human would attend to information at two levels: (i) the fields (macro level) and (ii) the values within the field (micro level). Further, a human would continue attending to a field for a few timesteps till all the information from that field has been rendered and then never return back to this field (because there is nothing left to say about it). To capture this behavior we use (i) a fused bifocal attention mechanism which exploits and combines this micro and macro level information and (ii) a gated orthogonalization mechanism which tries to ensure that a field is remembered for a few time steps and then forgotten. We experiment with a recently released dataset which contains fact tables about people and their corresponding one line biographical descriptions in English. In addition, we also introduce two similar datasets for French and German. Our experiments show that the proposed model gives 21% relative improvement over a recently proposed state of the art method and 10% relative improvement over basic seq2seq models. The code and the datasets developed as a part of this work are publicly available.

Parag Jain, Priyanka Agrawal, Abhijit Mishra et al.

Existing Natural Language Generation (NLG) systems are weak AI systems and exhibit limited capabilities when language generation tasks demand higher levels of creativity, originality and brevity. Effective solutions or, at least evaluations of modern NLG paradigms for such creative tasks have been elusive, unfortunately. This paper introduces and addresses the task of coherent story generation from independent descriptions, describing a scene or an event. Towards this, we explore along two popular text-generation paradigms -- (1) Statistical Machine Translation (SMT), posing story generation as a translation problem and (2) Deep Learning, posing story generation as a sequence to sequence learning problem. In SMT, we chose two popular methods such as phrase based SMT (PB-SMT) and syntax based SMT (SYNTAX-SMT) to `translate' the incoherent input text into stories. We then implement a deep recurrent neural network (RNN) architecture that encodes sequence of variable length input descriptions to corresponding latent representations and decodes them to produce well formed comprehensive story like summaries. The efficacy of the suggested approaches is demonstrated on a publicly available dataset with the help of popular machine translation and summarization evaluation metrics.

Ramandeep S Randhawa, Parag Jain, Gagan Madan

We propose a new algorithm for topic modeling, Vec2Topic, that identifies the main topics in a corpus using semantic information captured via high-dimensional distributed word embeddings. Our technique is unsupervised and generates a list of topics ranked with respect to importance. We find that it works better than existing topic modeling techniques such as Latent Dirichlet Allocation for identifying key topics in user-generated content, such as emails, chats, etc., where topics are diffused across the corpus. We also find that Vec2Topic works equally well for non-user generated content, such as papers, reports, etc., and for small corpora such as a single-document.