arXiv subjects

Soham Dan

Publications and source records attributed to Soham Dan.

At least 37 records · Page 2Linked to original sources

arXiv2025

On the Utility of Domain-Adjacent Fine-Tuned Model Ensembles for Few-shot Problems

Large Language Models (LLMs) have been observed to perform well on a wide range of downstream tasks when fine-tuned on domain-specific data. However, such data may not be readily available in many applications, motivating zero-shot or few-shot approaches using domain-adjacent models. While several fine-tuned models for various tasks are available, finding an appropriate domain-adjacent model for a given task is often not straight forward. In this paper, we study DAFT-E, a framework that utilizes an Ensemble of Domain-Adjacent Fine-Tuned Foundation Models for few-shot problems. We show that for zero-shot problems, this ensembling method provides an accuracy performance close to that of the single best model. With few-shot problems, this performance improves further, at which point DEFT-E can outperform any single domain-adjacent model while requiring much less data for domain-specific fine-tuning.

cs.CL↗

arXiv2025

Large Language Model Confidence Estimation via Black-Box Access

Estimating uncertainty or confidence in the responses of a model can be significant in evaluating trust not only in the responses, but also in the model as a whole. In this paper, we explore the problem of estimating confidence for responses of large language models (LLMs) with simply black-box or query access to them. We propose a simple and extensible framework where, we engineer novel features and train a (interpretable) model (viz. logistic regression) on these features to estimate the confidence. We empirically demonstrate that our simple framework is effective in estimating confidence of Flan-ul2, Llama-13b, Mistral-7b and GPT-4 on four benchmark Q\&A tasks as well as of Pegasus-large and BART-large on two benchmark summarization tasks with it surpassing baselines by even over $10\%$ (on AUROC) in some cases. Additionally, our interpretable approach provides insight into features that are predictive of confidence, leading to the interesting and useful discovery that our confidence models built for one LLM generalize zero-shot across others on a given dataset.

cs.CL↗

arXiv2025

Can LLMs reason over extended multilingual contexts? Towards long-context evaluation beyond retrieval and haystacks

Existing multilingual long-context benchmarks, often based on the popular needle-in-a-haystack test, primarily evaluate a model's ability to locate specific information buried within irrelevant texts. However, such a retrieval-centric approach is myopic and inherently limited, as successful recall alone does not indicate a model's capacity to reason over extended contexts. Moreover, these benchmarks are susceptible to data leakage, short-circuiting, and risk making the evaluation a priori identifiable. To address these limitations, we introduce MLRBench, a new synthetic benchmark for multilingual long-context reasoning. Unlike existing benchmarks, MLRBench goes beyond surface-level retrieval by including tasks that assess multi-hop inference, aggregation, and epistemic reasoning. Spanning seven languages, MLRBench is designed to be parallel, resistant to leakage, and scalable to arbitrary context lengths. Our extensive experiments with an open-weight large language model (LLM) reveal a pronounced gap between high- and low-resource languages, particularly for tasks requiring the model to aggregate multiple facts or predict the absence of information. We also find that, in multilingual settings, LLMs effectively utilize less than 30% of their claimed context length. Although off-the-shelf Retrieval Augmented Generation helps alleviate this to a certain extent, it does not solve the long-context problem. We open-source MLRBench to enable future research in improved evaluation and training of multilingual LLMs.

cs.CL↗

arXiv2025

AssertionBench: A Benchmark to Evaluate Large-Language Models for Assertion Generation

Assertions have been the de facto collateral for simulation-based and formal verification of hardware designs for over a decade. The quality of hardware verification, \ie, detection and diagnosis of corner-case design bugs, is critically dependent on the quality of the assertions. There has been a considerable amount of research leveraging a blend of data-driven statistical analysis and static analysis to generate high-quality assertions from hardware design source code and design execution trace data. Despite such concerted effort, all prior research struggles to scale to industrial-scale large designs, generates too many low-quality assertions, often fails to capture subtle and non-trivial design functionality, and does not produce any easy-to-comprehend explanations of the generated assertions to understand assertions' suitability to different downstream validation tasks. Recently, with the advent of Large-Language Models (LLMs), there has been a widespread effort to leverage prompt engineering to generate assertions. However, there is little effort to quantitatively establish the effectiveness and suitability of various LLMs for assertion generation. In this paper, we present AssertionBench, a novel benchmark to evaluate LLMs' effectiveness for assertion generation quantitatively. AssertioBench contains 100 curated Verilog hardware designs from OpenCores and formally verified assertions for each design generated from GoldMine and HARM. We use AssertionBench to compare state-of-the-art LLMs to assess their effectiveness in inferring functionally correct assertions for hardware designs. Our experiments demonstrate how LLMs perform relative to each other, the benefits of using more in-context exemplars in generating a higher fraction of functionally correct assertions, and the significant room for improvement for LLM-based assertion generators.

cs.SE↗

arXiv2025

Are LLMs Ready for Practical Adoption for Assertion Generation?

Assertions have been the de facto collateral for simulation-based and formal verification of hardware designs for over a decade. The quality of hardware verification, i.e., detection and diagnosis of corner-case design bugs, is critically dependent on the quality of the assertions. With the onset of generative AI such as Transformers and Large-Language Models (LLMs), there has been a renewed interest in developing novel, effective, and scalable techniques of generating functional and security assertions from design source code. While there have been recent works that use commercial-of-the-shelf (COTS) LLMs for assertion generation, there is no comprehensive study in quantifying the effectiveness of LLMs in generating syntactically and semantically correct assertions. In this paper, we first discuss AssertionBench from our prior work, a comprehensive set of designs and assertions to quantify the goodness of a broad spectrum of COTS LLMs for the task of assertion generations from hardware design source code. Our key insight was that COTS LLMs are not yet ready for prime-time adoption for assertion generation as they generate a considerable fraction of syntactically and semantically incorrect assertions. Motivated by the insight, we propose AssertionLLM, a first of its kind LLM model, specifically fine-tuned for assertion generation. Our initial experimental results show that AssertionLLM considerably improves the semantic and syntactic correctness of the generated assertions over COTS LLMs.

cs.LG↗

arXiv2025

Few-shot Policy (de)composition in Conversational Question Answering

The task of policy compliance detection (PCD) is to determine if a scenario is in compliance with respect to a set of written policies. In a conversational setting, the results of PCD can indicate if clarifying questions must be asked to determine compliance status. Existing approaches usually claim to have reasoning capabilities that are latent or require a large amount of annotated data. In this work, we propose logical decomposition for policy compliance (LDPC): a neuro-symbolic framework to detect policy compliance using large language models (LLMs) in a few-shot setting. By selecting only a few exemplars alongside recently developed prompting techniques, we demonstrate that our approach soundly reasons about policy compliance conversations by extracting sub-questions to be answered, assigning truth values from contextual information, and explicitly producing a set of logic statements from the given policies. The formulation of explicit logic graphs can in turn help answer PCDrelated questions with increased transparency and explainability. We apply this approach to the popular PCD and conversational machine reading benchmark, ShARC, and show competitive performance with no task-specific finetuning. We also leverage the inherently interpretable architecture of LDPC to understand where errors occur, revealing ambiguities in the ShARC dataset and highlighting the challenges involved with reasoning for conversational question answering.

cs.CL↗

arXiv2024

NAVCON: A Cognitively Inspired and Linguistically Grounded Corpus for Vision and Language Navigation

We present NAVCON, a large-scale annotated Vision-Language Navigation (VLN) corpus built on top of two popular datasets (R2R and RxR). The paper introduces four core, cognitively motivated and linguistically grounded, navigation concepts and an algorithm for generating large-scale silver annotations of naturally occurring linguistic realizations of these concepts in navigation instructions. We pair the annotated instructions with video clips of an agent acting on these instructions. NAVCON contains 236, 316 concept annotations for approximately 30, 0000 instructions and 2.7 million aligned images (from approximately 19, 000 instructions) showing what the agent sees when executing an instruction. To our knowledge, this is the first comprehensive resource of navigation concepts. We evaluated the quality of the silver annotations by conducting human evaluation studies on NAVCON samples. As further validation of the quality and usefulness of the resource, we trained a model for detecting navigation concepts and their linguistic realizations in unseen instructions. Additionally, we show that few-shot learning with GPT-4o performs well on this task using large-scale silver annotations of NAVCON.

cs.CL↗

arXiv2024

Benchmarking LLM Guardrails in Handling Multilingual Toxicity

With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiveness in handling multilingual toxic inputs remains unclear. In this work, we introduce a comprehensive multilingual test suite, spanning seven datasets and over ten languages, to benchmark the performance of state-of-the-art guardrails. We also investigates the resilience of guardrails against recent jailbreaking techniques, and assess the impact of in-context safety policies and language resource availability on guardrails' performance. Our findings show that existing guardrails are still ineffective at handling multilingual toxicity and lack robustness against jailbreaking prompts. This work aims to identify the limitations of guardrails and to build a more reliable and trustworthy LLMs in multilingual scenarios.

cs.CL↗

arXiv2024

Large Language Models can be Strong Self-Detoxifiers

Reducing the likelihood of generating harmful and toxic output is an essential task when aligning large language models (LLMs). Existing methods mainly rely on training an external reward model (i.e., another language model) or fine-tuning the LLM using self-generated data to influence the outcome. In this paper, we show that LLMs have the capability of self-detoxification without the use of an additional reward model or re-training. We propose \textit{Self-disciplined Autoregressive Sampling (SASA)}, a lightweight controlled decoding algorithm for toxicity reduction of LLMs. SASA leverages the contextual representations from an LLM to learn linear subspaces characterizing toxic v.s. non-toxic output in analytical forms. When auto-completing a response token-by-token, SASA dynamically tracks the margin of the current output to steer the generation away from the toxic subspace, by adjusting the autoregressive sampling strategy. Evaluated on LLMs of different scale and nature, namely Llama-3.1-Instruct (8B), Llama-2 (7B), and GPT2-L models with the RealToxicityPrompts, BOLD, and AttaQ benchmarks, SASA markedly enhances the quality of the generated sentences relative to the original models and attains comparable performance to state-of-the-art detoxification techniques, significantly reducing the toxicity level by only using the LLM's internal representations.

cs.LG↗

arXiv2024

Higher-Order Graphon Theory: Fluctuations, Degeneracies, and Inference

Exchangeable random graphs, which include some of the most widely studied network models, have emerged as the mainstay of statistical network analysis in recent years. Graphons, which are the central objects in graph limit theory, provide a natural way to sample exchangeable random graphs. It is well known that network moments (motif/subgraph counts) identify a graphon (up to an isomorphism), hence, understanding the sampling distribution of subgraph counts in random graphs sampled from a graphon is pivotal for nonparametric network inference. In this paper, we derive the joint asymptotic distribution of any finite collection of network moments in random graphs sampled from a graphon, that includes both the non-degenerate case (where the distribution is Gaussian) as well as the degenerate case (where the distribution has both Gaussian or non-Gaussian components). This provides the higher-order fluctuation theory for subgraph counts in the graphon model. We also develop a novel multiplier bootstrap for graphons that consistently approximates the limiting distribution of the network moments (both in the Gaussian and non-Gaussian regimes). Using this and a procedure for testing degeneracy, we construct joint confidence sets for any finite collection of motif densities. This provides a general framework for statistical inference based on network moments in the graphon model. To illustrate the broad scope of our results we also consider the problem of detecting global structure (that is, testing whether the graphon is a constant function) based on small subgraphs. We propose a consistent test for this problem, invoking celebrated results on quasi-random graphs, and derive its limiting distribution both under the null and the alternative.

math.ST↗

arXiv2024

Larimar: Large Language Models with Episodic Memory Control

Efficient and accurate updating of knowledge stored in Large Language Models (LLMs) is one of the most pressing research challenges today. This paper presents Larimar - a novel, brain-inspired architecture for enhancing LLMs with a distributed episodic memory. Larimar's memory allows for dynamic, one-shot updates of knowledge without the need for computationally expensive re-training or fine-tuning. Experimental results on multiple fact editing benchmarks demonstrate that Larimar attains accuracy comparable to most competitive baselines, even in the challenging sequential editing setup, but also excels in speed - yielding speed-ups of 8-10x depending on the base LLM - as well as flexibility due to the proposed architecture being simple, LLM-agnostic, and hence general. We further provide mechanisms for selective fact forgetting, information leakage prevention, and input context length generalization with Larimar and show their effectiveness. Our code is available at https://github.com/IBM/larimar

cs.LG↗

arXiv2024

Multilingual Needle in a Haystack: Investigating Long-Context Behavior of Multilingual Large Language Models

While recent large language models (LLMs) demonstrate remarkable abilities in responding to queries in diverse languages, their ability to handle long multilingual contexts is unexplored. As such, a systematic evaluation of the long-context capabilities of LLMs in multilingual settings is crucial, specifically in the context of information retrieval. To address this gap, we introduce the MultiLingual Needle-in-a-Haystack (MLNeedle) test, designed to assess a model's ability to retrieve relevant information (the needle) from a collection of multilingual distractor texts (the haystack). This test serves as an extension of the multilingual question-answering task, encompassing both monolingual and cross-lingual retrieval. We evaluate four state-of-the-art LLMs on MLNeedle. Our findings reveal that model performance can vary significantly with language and needle position. Specifically, we observe that model performance is the lowest when the needle is (i) in a language outside the English language family and (ii) located in the middle of the input context. Furthermore, although some models claim a context size of $8k$ tokens or greater, none demonstrate satisfactory cross-lingual retrieval performance as the context length increases. Our analysis provides key insights into the long-context behavior of LLMs in multilingual settings to guide future evaluation protocols. To our knowledge, this is the first study to investigate the multilingual long-context behavior of LLMs.

cs.CL↗

arXiv2024

Needle in the Haystack for Memory Based Large Language Models

Current large language models (LLMs) often perform poorly on simple fact retrieval tasks. Here we investigate if coupling a dynamically adaptable external memory to a LLM can alleviate this problem. For this purpose, we test Larimar, a recently proposed language model architecture which uses an external associative memory, on long-context recall tasks including passkey and needle-in-the-haystack tests. We demonstrate that the external memory of Larimar, which allows fast write and read of an episode of text samples, can be used at test time to handle contexts much longer than those seen during training. We further show that the latent readouts from the memory (to which long contexts are written) control the decoder towards generating correct outputs, with the memory stored off of the GPU. Compared to existing transformer-based LLM architectures for long-context recall tasks that use larger parameter counts or modified attention mechanisms, a relatively smaller size Larimar is able to maintain strong performance without any task-specific training or training on longer contexts.

cs.CL↗

arXiv2024

CTBench: A Comprehensive Benchmark for Evaluating Language Model Capabilities in Clinical Trial Design

CTBench is introduced as a benchmark to assess language models (LMs) in aiding clinical study design. Given study-specific metadata, CTBench evaluates AI models' ability to determine the baseline features of a clinical trial (CT), which include demographic and relevant features collected at the trial's start from all participants. These baseline features, typically presented in CT publications (often as Table 1), are crucial for characterizing study cohorts and validating results. Baseline features, including confounders and covariates, are also necessary for accurate treatment effect estimation in studies involving observational data. CTBench consists of two datasets: "CT-Repo," containing baseline features from 1,690 clinical trials sourced from clinicaltrials.gov, and "CT-Pub," a subset of 100 trials with more comprehensive baseline features gathered from relevant publications. Two LM-based evaluation methods are developed to compare the actual baseline feature lists against LM-generated responses. "ListMatch-LM" and "ListMatch-BERT" use GPT-4o and BERT scores (at various thresholds), respectively, for evaluation. To establish baseline results, advanced prompt engineering techniques using LLaMa3-70B-Instruct and GPT-4o in zero-shot and three-shot learning settings are applied to generate potential baseline features. The performance of GPT-4o as an evaluator is validated through human-in-the-loop evaluations on the CT-Pub dataset, where clinical experts confirm matches between actual and LM-generated features. The results highlight a promising direction with significant potential for improvement, positioning CTBench as a useful tool for advancing research on AI in CT design and potentially enhancing the efficacy and robustness of CTs.

cs.CL↗

arXiv2024

NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models

Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their widespread applicability. While enforcing sparsity at various levels of the model architecture has found promise in addressing scaling and efficiency issues, there remains a disconnect between how sparsity affects network topology. Inspired by brain neuronal networks, we explore sparsity approaches through the lens of network topology. Specifically, we exploit mechanisms seen in biological networks, such as preferential attachment and redundant synapse pruning, and show that principled, model-agnostic sparsity approaches are performant and efficient across diverse NLP tasks, spanning both classification (such as natural language inference) and generation (summarization, machine translation), despite our sole objective not being optimizing performance. NeuroPrune is competitive with (or sometimes superior to) baselines on performance and can be up to $10$x faster in terms of training time for a given level of sparsity, simultaneously exhibiting measurable improvements in inference time in many cases.

cs.LG↗

arXiv2024

API-BLEND: A Comprehensive Corpora for Training and Benchmarking API LLMs

There is a growing need for Large Language Models (LLMs) to effectively use tools and external Application Programming Interfaces (APIs) to plan and complete tasks. As such, there is tremendous interest in methods that can acquire sufficient quantities of train and test data that involve calls to tools / APIs. Two lines of research have emerged as the predominant strategies for addressing this challenge. The first has focused on synthetic data generation techniques, while the second has involved curating task-adjacent datasets which can be transformed into API / Tool-based tasks. In this paper, we focus on the task of identifying, curating, and transforming existing datasets and, in turn, introduce API-BLEND, a large corpora for training and systematic testing of tool-augmented LLMs. The datasets mimic real-world scenarios involving API-tasks such as API / tool detection, slot filling, and sequencing of the detected APIs. We demonstrate the utility of the API-BLEND dataset for both training and benchmarking purposes.

cs.CL↗

arXiv2024

On the Calibration of Multilingual Question Answering LLMs

Multilingual pre-trained Large Language Models (LLMs) are incredibly effective at Question Answering (QA), a core task in Natural Language Understanding, achieving high accuracies on several multilingual benchmarks. However, little is known about how well their confidences are calibrated. In this paper, we comprehensively benchmark the calibration of several multilingual LLMs (MLLMs) on a variety of QA tasks. We perform extensive experiments, spanning encoder-only, encoder-decoder, and decoder-only QA models (size varying from 110M to 7B parameters) and diverse languages, including both high- and low-resource ones. We study different dimensions of calibration in in-distribution, out-of-distribution, and cross-lingual transfer settings, and investigate strategies to improve it, including post-hoc methods and regularized fine-tuning. For decoder-only LLMs such as LlaMa2, we additionally find that in-context learning improves confidence calibration on multilingual data. We also conduct several ablation experiments to study the effect of language distances, language corpus size, and model size on calibration, and how multilingual models compare with their monolingual counterparts for diverse tasks and languages. Our experiments suggest that the multilingual QA models are poorly calibrated for languages other than English and incorporating a small set of cheaply translated multilingual samples during fine-tuning/calibration effectively enhances the calibration performance.

cs.CL↗

arXiv2024

On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning

Text-based reinforcement learning involves an agent interacting with a fictional environment using observed text and admissible actions in natural language to complete a task. Previous works have shown that agents can succeed in text-based interactive environments even in the complete absence of semantic understanding or other linguistic capabilities. The success of these agents in playing such games suggests that semantic understanding may not be important for the task. This raises an important question about the benefits of LMs in guiding the agents through the game states. In this work, we show that rich semantic understanding leads to efficient training of text-based RL agents. Moreover, we describe the occurrence of semantic degeneration as a consequence of inappropriate fine-tuning of language models in text-based reinforcement learning (TBRL). Specifically, we describe the shift in the semantic representation of words in the LM, as well as how it affects the performance of the agent in tasks that are semantically similar to the training games. We believe these results may help develop better strategies to fine-tune agents in text-based RL scenarios.

cs.CL↗